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

    Neuronpedia

    INDEX
    Explanations

    Thursday FYI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     like
    -1.04
    為に
    -0.96
     Of
    -0.93
    imanapun
    -0.92
    少々
    -0.87
    様な
    -0.87
    つづく
    -0.85
     was
    -0.84
     OF
    -0.83
    んですよ
    -0.83
    POSITIVE LOGITS
     vinaigre
    1.20
     kompeti
    1.14
     poitrine
    1.11
     dager
    1.11
     ferien
    1.10
     ferie
    1.09
    <bos>
    1.09
     eier
    1.05
    formazione
    1.05
     assise
    1.04
    Act Density 0.000%

    No Known Activations