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

    Neuronpedia

    INDEX
    Explanations

    origin, production, or availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ؛
    0.91
    ।
    0.88
    .}
    0.85
    。）
    0.84
    。
    0.84
    。（
    0.82
    ।)
    0.81
     कहे
    0.79
    .")
    0.78
    )।
    0.78
    POSITIVE LOGITS
     primarily
    1.57
     in
    1.47
     mainly
    1.46
     as
    1.43
     at
    1.37
     mostly
    1.36
     by
    1.36
     on
    1.35
     within
    1.32
     with
    1.29
    Act Density 0.346%

    No Known Activations