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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (keys
    -0.07
    monary
    -0.07
    печ
    -0.07
     ffi
    -0.07
     lid
    -0.07
    ्यप
    -0.06
     trough
    -0.06
     dq
    -0.06
    gi
    -0.06
     L
    -0.06
    POSITIVE LOGITS
    跳
    0.07
     sewer
    0.06
     aggrav
    0.06
     пис
    0.06
     đai
    0.06
     PAT
    0.06
     подготов
    0.06
    題
    0.06
    PAT
    0.06
     ат
    0.06
    Act Density 0.148%

    No Known Activations