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

    Neuronpedia

    INDEX
    Explanations

    probability and likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.86
    یم
    0.77
    </h3>
    0.72
     impuls
    0.70
    ।
    0.70
     Χ
    0.68
     it
    0.67
     are
    0.67
     as
    0.66
    ors
    0.65
    POSITIVE LOGITS
    in
    1.08
    اك
    0.88
    is
    0.82
    ار
    0.79
    ை
    0.76
    你
    0.76
    на
    0.71
    מ
    0.71
    不
    0.71
    ec
    0.70
    Act Density 0.327%

    No Known Activations