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

    Neuronpedia

    INDEX
    Explanations

    describes / performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.67
    t
    0.63
    一
    0.56
    aing
    0.50
     phases
    0.49
    r
    0.49
    y
    0.49
    ール
    0.48
    気になる
    0.46
    droid
    0.46
    POSITIVE LOGITS
     Presiden
    0.59
    烺
    0.57
     হয
    0.57
     อ่ะ
    0.55
    眥
    0.55
     Cliente
    0.55
     Neces
    0.55
     Vậy
    0.55
     Desember
    0.55
     Daven
    0.54
    Act Density 0.000%

    No Known Activations