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

    Neuronpedia

    INDEX
    Explanations

    i want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.75
     (
    0.69
     "
    0.65
    .
    0.59
     the
    0.59
    ;
    0.57
    0.56
     and
    0.56
     a
    0.55
     using
    0.55
    POSITIVE LOGITS
    dayspecial
    0.95
     veoma
    0.92
    <unused1815>
    0.89
     йөкләү
    0.89
     veľmi
    0.87
     estremamente
    0.87
    力
    0.87
    illées
    0.87
     дуже
    0.87
    commonByteArray
    0.86
    Act Density 0.322%

    No Known Activations