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

    Neuronpedia

    INDEX
    Explanations

    sometimes, high, long, among

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    👫
    0.49
    ॓
    0.46
    궬
    0.46
    ϙ
    0.45
    💏
    0.45
     musculaire
    0.45
    mataspid
    0.45
    מ
    0.45
    تاة
    0.44
    \%,
    0.44
    POSITIVE LOGITS
    in
    0.61
     {
    0.52
    0.51
     Int
    0.46
    t
    0.46
     Description
    0.46
     want
    0.45
     sneak
    0.45
     Type
    0.44
     have
    0.44
    Act Density 0.000%

    No Known Activations