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

    Neuronpedia

    INDEX
    Explanations

    availability

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     אלף
    -0.07
    מאה
    -0.07
    较多
    -0.07
    גי
    -0.07
    _MASTER
    -0.06
     harmonic
    -0.06
    ek
    -0.06
    枰
    -0.06
     puzzled
    -0.06
    選び
    -0.06
    POSITIVE LOGITS
     truth
    0.08
    imientos
    0.08
     Martha
    0.08
    إعلام
    0.07
    会
    0.07
    heritance
    0.07
    垦
    0.07
     currencies
    0.07
    حضور
    0.07
     Veget
    0.07
    Act Density 0.009%

    No Known Activations