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

    Neuronpedia

    INDEX
    Explanations

    LaTeX document structure and content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mí
    0.39
     posljed
    0.39
     мелдеш
    0.38
     comunque
    0.38
     gird
    0.38
     masas
    0.38
    诞生
    0.37
     dernière
    0.37
    ີ້
    0.37
     ܡ
    0.37
    POSITIVE LOGITS
    keyword
    0.55
    abstract
    0.51
     Keyword
    0.43
    Abstract
    0.41
    small
    0.40
     Motivation
    0.40
     abstracto
    0.39
     abstract
    0.39
    נדה
    0.39
    Motivation
    0.38
    Act Density 0.000%

    No Known Activations