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

    Neuronpedia

    INDEX
    Explanations

    cause, source, function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raccoon
    0.48
     personnes
    0.47
    आगे
    0.46
     ny
    0.45
    ঃখ
    0.44
    庝
    0.44
    น่า
    0.44
    ၿ
    0.44
    虺
    0.44
     burung
    0.43
    POSITIVE LOGITS
     Scores
    0.44
     ';
    0.44
    છા
    0.44
    d
    0.43
    AV
    0.41
    TABLE
    0.40
     فانه
    0.40
     Ávila
    0.40
    scores
    0.40
    N
    0.39
    Act Density 0.001%

    No Known Activations