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

    Neuronpedia

    INDEX
    Explanations

    Code or special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MSG
    -0.06
    책
    -0.06
    OperationException
    -0.06
    /set
    -0.06
     spies
    -0.06
    .Adam
    -0.06
    _upload
    -0.06
    _BLOCKS
    -0.06
     массив
    -0.06
    -ext
    -0.06
    POSITIVE LOGITS
    onesia
    0.07
     Angeles
    0.07
     constituents
    0.06
    tvrt
    0.06
     decoding
    0.06
     Datum
    0.06
     ради
    0.06
    CLUDING
    0.06
     книж
    0.06
     turkey
    0.06
    Act Density 0.000%

    No Known Activations