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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    频
    -0.07
     فأ
    -0.06
    _K
    -0.06
    营地
    -0.06
    春晚
    -0.06
    榧
    -0.06
    ﳐ
    -0.06
    此次
    -0.06
    (ps
    -0.06
     Exposure
    -0.06
    POSITIVE LOGITS
    ยาว
    0.08
    Idle
    0.07
    绰
    0.07
    radouro
    0.07
     liquidity
    0.07
     bogus
    0.07
     schwar
    0.07
     Jwt
    0.07
    SourceType
    0.07
    wła
    0.07
    Act Density 0.001%

    No Known Activations