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

    Neuronpedia

    INDEX
    Explanations

    graphics and analytics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    1.63
    1.21
    ing
    0.96
    ong
    0.95
    of
    0.95
    Type
    0.95
    A
    0.94
     was
    0.92
    一
    0.92
    G
    0.91
    POSITIVE LOGITS
    x
    1.24
    ли
    1.23
    1.11
     නිෂ්
    1.09
    ⓪
    1.02
     ກຳ
    0.98
    lerinin
    0.98
    ᱐
    0.98
     اسرائی
    0.97
    ۰
    0.96
    Act Density 0.253%

    No Known Activations