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

    Neuronpedia

    INDEX
    Explanations

    Python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     patron
    -0.07
     Christopher
    -0.07
    Chunks
    -0.07
    젴
    -0.06
    localctx
    -0.06
     treasures
    -0.06
    aus
    -0.06
     уникальн
    -0.06
    _PRODUCT
    -0.06
    场上
    -0.06
    POSITIVE LOGITS
    ('',
    0.08
     PageSize
    0.07
    嗦
    0.06
    inflate
    0.06
     sms
    0.06
    czył
    0.06
    perate
    0.06
     fkk
    0.06
     revoked
    0.06
    =form
    0.06
    Act Density 0.071%

    No Known Activations