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

    Neuronpedia

    INDEX
    Explanations

    file extensions and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    -2.58
     this
    -2.25
     for
    -2.22
     There
    -2.19
     and
    -1.96
     If
    -1.91
     with
    -1.79
     from
    -1.77
     or
    -1.71
     on
    -1.69
    POSITIVE LOGITS
    热水
    1.59
    ztes
    1.55
    quelles
    1.51
    そして
    1.50
    1.47
    では
    1.45
    がありますが
    1.41
    <bos>
    1.40
     Produits
    1.39
    もあって
    1.39
    Act Density 0.050%

    No Known Activations