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

    Neuronpedia

    INDEX
    Explanations

    integer

    np_max-act · gemini-2.0-flash

    The neuron is detecting floating‐point (decimal) numeric literals in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Contains
    -0.07
    ��
    -0.06
    inar
    -0.06
    usk
    -0.06
     Мак
    -0.06
     never
    -0.06
    imientos
    -0.06
    :$
    -0.06
    елов
    -0.06
    diği
    -0.06
    POSITIVE LOGITS
    ISTRIBUT
    0.07
     हव
    0.07
     hurdle
    0.06
    -font
    0.06
    .DotNetBar
    0.06
     �
    0.06
     експ
    0.06
    wij
    0.06
     jednotliv
    0.06
    였다
    0.06
    Act Density 0.002%

    No Known Activations