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

    Neuronpedia

    INDEX
    Explanations

    with unseen or achievable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ера
    0.50
    ل
    0.48
    е
    0.46
    ᵉ
    0.45
     खान
    0.43
    лера
    0.42
    у
    0.42
     Überg
    0.42
     තර
    0.42
    ൻ
    0.42
    POSITIVE LOGITS
    调度
    0.50
     heller
    0.41
    暴
    0.41
     winkel
    0.41
    <unused36>
    0.40
    制造
    0.40
     مقام
    0.40
    扳
    0.40
     prič
    0.39
     histo
    0.39
    Act Density 0.001%

    No Known Activations