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

    Neuronpedia

    INDEX
    Explanations

    command window learning support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    1.56
    The
    1.46
    This
    1.35
    For
    1.31
    el
    1.29
    1
    1.27
    You
    1.26
    (
    1.26
    We
    1.24
    en
    1.22
    POSITIVE LOGITS
    𝐥
    1.20
     tannins
    1.09
     oversight
    1.08
    ﺰ
    1.08
     adjusting
    1.05
     čas
    1.05
    रूम
    1.04
    ﻴ
    1.04
     humidity
    1.03
    ﻜ
    1.02
    Act Density 0.524%

    No Known Activations