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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and symbols

    np_max-act · gemini-2.0-flash

    The neuron activates on references to classifying or matching punctuation characters.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     aerobic
    -0.07
     marketer
    -0.06
     dans
    -0.06
     enfer
    -0.06
    Exceptions
    -0.06
     transformer
    -0.06
    ait
    -0.06
    氏
    -0.06
    [#
    -0.06
    *****
↵
    -0.06
    POSITIVE LOGITS
     preseason
    0.07
     vystav
    0.07
    �
    0.07
     الوط
    0.07
     plung
    0.07
     summit
    0.06
     swirl
    0.06
    readonly
    0.06
    ']):
    0.06
    -notification
    0.06
    Act Density 0.010%

    No Known Activations