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

    Neuronpedia

    INDEX
    Explanations

    exception handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Six
    0.41
    ingular
    0.39
     folder
    0.36
    SIX
    0.36
     phóng
    0.36
     優
    0.36
    nabla
    0.35
    PreferenceKey
    0.35
    ્ર
    0.35
    Magn
    0.35
    POSITIVE LOGITS
     oli
    0.37
    >`;
    0.37
    kii
    0.35
    wertung
    0.35
    гел
    0.35
     african
    0.34
     thisComponent
    0.34
    胗
    0.34
    خذ
    0.34
     Spots
    0.34
    Act Density 0.001%

    No Known Activations