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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens—especially floating-point constants—highlighting occurrences of numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Col
    -0.07
     presumption
    -0.07
     metam
    -0.07
     hôm
    -0.07
    ().
    -0.06
    .Batch
    -0.06
    상을
    -0.06
    .authorization
    -0.06
    ћ
    -0.06
    份
    -0.06
    POSITIVE LOGITS
    shint
    0.06
     이러한
    0.06
    UTDOWN
    0.06
    ीए
    0.06
     проек
    0.06
    -leading
    0.06
     Sharma
    0.05
     Pé
    0.05
     dolay
    0.05
     �
    0.05
    Act Density 0.020%

    No Known Activations