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

    Neuronpedia

    INDEX
    Explanations

    stock availability and levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    —
    0.71
    ,
    0.68
    .`);
    0.66
    ,’
    0.61
     eux
    0.61
     написа
    0.59
    ,.
    0.58
     наз
    0.57
    תה
    0.57
    {
    0.56
    POSITIVE LOGITS
    il
    1.09
    ak
    1.04
    id
    0.90
    ik
    0.89
    ie
    0.87
    ou
    0.85
    s
    0.84
    en
    0.82
    ड
    0.80
    ah
    0.79
    Act Density 0.007%

    No Known Activations