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

    Neuronpedia

    INDEX
    Explanations

    world news links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %
    0.61
    .
    0.61
     p
    0.60
     since
    0.55
    :
    0.54
     having
    0.53
    /
    0.53
     pit
    0.53
    d
    0.53
     when
    0.53
    POSITIVE LOGITS
    ChooseCharacter
    0.88
    mois
    0.87
    lcnaf
    0.86
    <unused1680>
    0.86
     striis
    0.84
    Choisissez
    0.82
    欳
    0.82
    具体的な
    0.82
    सरकारी
    0.81
    <unused2089>
    0.80
    Act Density 0.005%

    No Known Activations