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

    Neuronpedia

    INDEX
    Explanations

    action, support, borrow, shall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polytopes
    1.12
     sects
    1.04
    𝘱
    1.03
     posicao
    1.02
     polytope
    1.02
    aço
    1.02
    ◽
    0.99
    كله
    0.98
    ﺂ
    0.96
    kontakt
    0.96
    POSITIVE LOGITS
     (
    0.89
    T
    0.83
    P
    0.83
    ↵↵
    0.81
    A
    0.80
    O
    0.77
    Is
    0.76
    J
    0.76
     in
    0.75
     of
    0.74
    Act Density 0.000%

    No Known Activations