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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recycl
    -0.09
    _UNSIGNED
    -0.09
    واجد
    -0.08
    รายการ
    -0.08
    elect
    -0.08
    vores
    -0.08
    rechter
    -0.08
     древ
    -0.07
     masked
    -0.07
    inyi
    -0.07
    POSITIVE LOGITS
    coef
    0.09
     coef
    0.09
     determined
    0.08
     calibr
    0.08
     fittings
    0.08
    完善
    0.08
     معلوم
    0.08
    看看
    0.08
     маълум
    0.07
    /logo
    0.07
    Act Density 0.093%

    No Known Activations