Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs

    np_max-act · gemini-2.0-flash

    mathematical functions and their properties, specifically relating to limits and differentiability in multiple variables.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on numeric literals (especially decimal numbers) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _cmos
    -0.08
    .Mask
    -0.07
    .Sqrt
    -0.06
    Ral
    -0.06
    JNIEnv
    -0.06
    fü
    -0.06
    .DateTimePicker
    -0.06
    _SO
    -0.06
     лог
    -0.06
    _placement
    -0.06
    POSITIVE LOGITS
    (domain
    0.07
    along
    0.07
    ((
    0.06
     disruptions
    0.06
     связ
    0.06
    首
    0.06
     altogether
    0.06
     Installing
    0.06
    (E
    0.06
     imposing
    0.06
    Act Density 0.008%

    No Known Activations