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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kw
    -0.07
    كال
    -0.06
    diag
    -0.06
    ********************
    -0.06
    ่วง
    -0.06
    867
    -0.06
    ющего
    -0.06
    fare
    -0.05
     الأول
    -0.05
     ine
    -0.05
    POSITIVE LOGITS
    动生成
    0.07
     Zah
    0.07
    07
    0.06
    Toronto
    0.06
    .setName
    0.06
     teklif
    0.06
    Tim
    0.06
     euler
    0.06
    .calls
    0.06
     hod
    0.06
    Act Density 0.008%

    No Known Activations