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

    Neuronpedia

    INDEX
    Explanations

    external contamination, Maven aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পৃথক
    0.39
    voy
    0.39
     conducting
    0.38
    "'
    0.37
    {{{
    0.37
     fet
    0.36
     wenden
    0.36
     समर्
    0.35
    这篇文章
    0.35
    ᅦ
    0.35
    POSITIVE LOGITS
    Ɩ
    0.41
    Plas
    0.38
    apods
    0.37
     Abelian
    0.36
     Perk
    0.36
    thickmathspace
    0.36
     Thos
    0.36
    USR
    0.36
     Plas
    0.36
     हु
    0.35
    Act Density 0.000%

    No Known Activations