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

    Neuronpedia

    INDEX
    Explanations

    bodybuilding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    0.37
    n
    0.37
    น
    0.36
    is
    0.35
    ด
    0.35
    ש
    0.35
    一脸
    0.34
    ayı
    0.33
    Kako
    0.33
    as
    0.32
    POSITIVE LOGITS
    യുടെ
    0.36
    stagram
    0.32
     osią
    0.31
     ఎక్కువగా
    0.30
    。<
    0.30
     Éireann
    0.30
    ،
    0.29
     enthusiasts
    0.29
    ”、
    0.29
    にとっては
    0.29
    Act Density 0.404%

    No Known Activations