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

    Neuronpedia

    INDEX
    Explanations

    async function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AK
    0.66
    Wildlife
    0.65
     आहेत
    0.64
     område
    0.63
     veineux
    0.63
    ках
    0.62
    URE
    0.62
     programação
    0.62
    radiative
    0.62
    Packages
    0.61
    POSITIVE LOGITS
     for
    1.30
     with
    0.93
     not
    0.91
     has
    0.86
     the
    0.86
     from
    0.84
     and
    0.83
     by
    0.80
     of
    0.79
    z
    0.78
    Act Density 0.039%

    No Known Activations