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

    Neuronpedia

    INDEX
    Explanations

    plans and pricing information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    &
    1.03
     rightly
    1.02
    of
    0.97
     rightfully
    0.96
    @
    0.92
    o
    0.90
    utorial
    0.88
    ity
    0.88
    things
    0.87
    how
    0.87
    POSITIVE LOGITS
    硬
    0.79
    splitLength
    0.76
    𝟭
    0.68
     iler
    0.67
     bitOp
    0.67
     лі
    0.67
     ningún
    0.65
     почина
    0.65
     Cure
    0.65
    嗮
    0.65
    Act Density 0.000%

    No Known Activations