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

    Neuronpedia

    INDEX
    Explanations

    number factorial expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doo
    0.78
     conduct
    0.75
     conducts
    0.72
     repressed
    0.64
     conducted
    0.63
     carried
    0.62
     NOR
    0.61
     tradition
    0.61
    やら
    0.61
     Fourteen
    0.61
    POSITIVE LOGITS
    %；
    1.18
    //}
    1.11
    ^{*}$,
    1.07
    %，
    1.07
     ;,
    1.06
    }^{*}$,
    1.05
    _;
    1.04
     !,
    1.04
    (),
    1.02
     :,
    1.01
    Act Density 0.373%

    No Known Activations