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

    Neuronpedia

    INDEX
    Explanations

    zip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _condition
    -0.07
    纳
    -0.07
    衝
    -0.07
    バン
    -0.06
    Make
    -0.06
     руков
    -0.06
    ปก
    -0.06
     CALC
    -0.06
    ạc
    -0.06
     readFile
    -0.06
    POSITIVE LOGITS
    ım
    0.09
    -twitter
    0.08
    弟
    0.07
     asteroids
    0.07
    社交
    0.07
    拿起
    0.07
    ida
    0.07
     lord
    0.07
     cytok
    0.07
     deployments
    0.07
    Act Density 0.003%

    No Known Activations