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

    Neuronpedia

    INDEX
    Explanations

    commentary and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agway
    0.46
    طن
    0.38
    emun
    0.36
    関係
    0.36
    诉
    0.35
    réal
    0.34
    합
    0.34
    viles
    0.34
    fans
    0.34
    느
    0.34
    POSITIVE LOGITS
     коммента
    0.49
     commentary
    0.49
     commenter
    0.48
     commenting
    0.46
    Commenting
    0.46
     comments
    0.43
     Commentary
    0.43
     Kommentar
    0.43
     comment
    0.43
     commented
    0.41
    Act Density 0.000%

    No Known Activations