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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron detects decimal numbers (floating‐point values), such as those appearing in subject‐classification codes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ubergraph
    -0.07
    ��
    -0.06
     Kurum
    -0.06
    ิสต
    -0.06
    TPL
    -0.06
    نوع
    -0.06
    Contained
    -0.06
    ίσ
    -0.06
     университ
    -0.06
    ию
    -0.06
    POSITIVE LOGITS
    没有
    0.07
     Patel
    0.06
     MAT
    0.06
     Barnett
    0.06
    58
    0.06
     пох
    0.06
    Arthur
    0.06
     sparks
    0.06
    leDb
    0.06
    257
    0.06
    Act Density 0.001%

    No Known Activations