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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation like `*`, `(`, `)`, `__`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.48
    1
    1.37
    9
    1.37
    8
    1.36
    4
    1.32
    5
    1.27
    3
    1.24
    7
    1.23
    6
    1.20
    2
    1.18
    POSITIVE LOGITS
    );
    1.23
     morphism
    1.06
    😧
    1.04
    ):
    1.02
     HSPB
    1.00
     morphisms
    0.97
     Subhanahu
    0.96
    是一个
    0.95
    😚
    0.93
     (__
    0.91
    Act Density 0.228%

    No Known Activations