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

    Neuronpedia

    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кает
    0.42
     (
    0.41
    ايا
    0.40
    ChoiceItemLayout
    0.40
    ，
    0.40
     cháy
    0.39
     advertiser
    0.38
    缎
    0.38
     तहत
    0.37
    يلي
    0.37
    POSITIVE LOGITS
    is
    0.63
    on
    0.61
    A
    0.57
    in
    0.55
    and
    0.51
    The
    0.50
    I
    0.50
    G
    0.50
    V
    0.49
    are
    0.49
    Act Density 0.135%

    No Known Activations