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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decoding
    -0.06
     oppon
    -0.06
    иту
    -0.06
    학생
    -0.06
    -device
    -0.06
    東京
    -0.06
    Ang
    -0.06
     ÜNİ
    -0.06
     �
    -0.06
    Shot
    -0.06
    POSITIVE LOGITS
     credential
    0.07
     sổ
    0.06
    书记
    0.06
    InInspector
    0.06
    /network
    0.06
    ]).
    0.06
    žití
    0.06
     vac
    0.06
    football
    0.06
     Frost
    0.06
    Act Density 0.112%

    No Known Activations