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

    Neuronpedia

    INDEX
    Explanations

    bullet points and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     레
    0.42
     capítulos
    0.41
    okat
    0.41
     मैंने
    0.40
     دارم
    0.40
     protective
    0.40
    مال
    0.40
    GY
    0.38
     самые
    0.38
     plaza
    0.38
    POSITIVE LOGITS
    Imper
    0.46
     imper
    0.40
    ूबी
    0.40
     Imper
    0.40
    ٰی
    0.39
    nesium
    0.38
    Feedback
    0.38
    tie
    0.38
    の違い
    0.38
    feedback
    0.37
    Act Density 0.000%

    No Known Activations