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

    Neuronpedia

    INDEX
    Explanations

    primates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.64
     Nutzung
    0.62
    3
    0.60
    ת
    0.59
    الم
    0.59
     Erfahrung
    0.59
     jedin
    0.58
    ప
    0.58
    ٥
    0.58
     ధ
    0.58
    POSITIVE LOGITS
    t
    0.87
    لیل
    0.75
    ut
    0.70
    f
    0.70
    it
    0.66
    ิ
    0.66
     VIH
    0.65
     primate
    0.64
    z
    0.63
     reforestation
    0.62
    Act Density 0.001%

    No Known Activations