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

    Neuronpedia

    INDEX
    Explanations

    huge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    体验
    -0.07
    _STEP
    -0.07
     Buffett
    -0.07
     الولا
    -0.07
    SSI
    -0.07
    סר
    -0.06
    LOCAL
    -0.06
    -states
    -0.06
     CHRIST
    -0.06
    niest
    -0.06
    POSITIVE LOGITS
     Tipo
    0.08
    معلومات
    0.08
    ']>
    0.08
    公共服务
    0.07
     kho
    0.07
     cervical
    0.07
     �
    0.07
     Human
    0.07
    趋向
    0.07
     kvinde
    0.07
    Act Density 0.006%

    No Known Activations