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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens—especially floating-point numbers used as size or parameter values (e.g. image size settings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    wer
    -0.07
    shot
    -0.06
     hour
    -0.06
    er
    -0.06
     Nexus
    -0.06
     sû
    -0.06
    >List
    -0.06
    >D
    -0.06
     scorer
    -0.06
     sino
    -0.06
    POSITIVE LOGITS
    014
    0.06
    等
    0.06
     नगर
    0.06
     setContent
    0.06
    assertCount
    0.06
    리즈
    0.06
     دين
    0.06
     τη
    0.06
     mutate
    0.06
    .argmax
    0.06
    Act Density 0.016%

    No Known Activations