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

    Neuronpedia

    INDEX
    Explanations

    Foucault, capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EL
    0.17
    AL
    0.17
     ادار
    0.16
    Ч
    0.16
    X
    0.16
    Sch
    0.15
    К
    0.15
    ST
    0.15
    இந்தப்
    0.15
     siè
    0.15
    POSITIVE LOGITS
     பாத
    0.19
    meric
    0.19
     Poems
    0.17
     poems
    0.17
     ვა
    0.17
     Asalamualaikum
    0.17
     composing
    0.17
    менты
    0.17
     insufficiency
    0.17
    cısı
    0.17
    Act Density 0.003%

    No Known Activations