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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Emb
    -0.08
     село
    -0.07
    _name
    -0.06
     SOL
    -0.06
    su
    -0.06
    /test
    -0.06
     concent
    -0.06
     thinks
    -0.06
     Rank
    -0.06
     Philip
    -0.06
    POSITIVE LOGITS
    서관
    0.07
     tá
    0.07
    เง
    0.06
     мат
    0.06
     관련
    0.06
     Graphics
    0.06
    IsValid
    0.06
    タン
    0.06
    _processing
    0.06
    (layers
    0.06
    Act Density 0.011%

    No Known Activations