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

    Neuronpedia

    INDEX
    Explanations

    entity relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cond
    0.39
     Ac
    0.37
    că
    0.37
    zw
    0.36
    ниципа
    0.35
    guj
    0.35
    Cond
    0.34
    dz
    0.34
    closePath
    0.34
    rrh
    0.34
    POSITIVE LOGITS
    INSTANCE
    0.52
     قيمة
    0.44
     значение
    0.44
    Value
    0.42
     VALUE
    0.42
     значення
    0.42
     FAX
    0.41
     values
    0.40
     ряд
    0.40
    SPD
    0.40
    Act Density 0.059%

    No Known Activations