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

    Neuronpedia

    INDEX
    Explanations

    tolerance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    istir
    0.44
    elijke
    0.43
    tumor
    0.43
    hors
    0.42
    rial
    0.42
    তির
    0.42
    tMap
    0.41
    ׄ
    0.41
    wählen
    0.41
    rennen
    0.41
    POSITIVE LOGITS
     tolerance
    1.06
     Tolerance
    1.04
    Tolerance
    1.02
     TOL
    0.99
     tolerancia
    0.97
     toler
    0.97
     Toler
    0.97
     Tol
    0.94
     tol
    0.93
     tolerant
    0.91
    Act Density 0.005%

    No Known Activations