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

    Neuronpedia

    INDEX
    Explanations

    virtual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Kel
    -0.07
    olics
    -0.06
     hepatitis
    -0.06
     embarrass
    -0.06
     MOS
    -0.06
     Bias
    -0.06
    MQ
    -0.06
     بايد
    -0.06
    _basic
    -0.06
    arya
    -0.06
    POSITIVE LOGITS
     fontWithName
    0.07
    inand
    0.06
    0.06
     araştır
    0.06
    غات
    0.06
    },
    0.06
    付
    0.06
    '],
    0.06
    //}}
    0.06
    sip
    0.06
    Act Density 0.002%

    No Known Activations