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

    Neuronpedia

    INDEX
    Explanations

    financial responsibilities and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    0.36
    ف
    0.34
    }>
    0.31
    كم
    0.29
    0.27
    دين
    0.27
     आईआई
    0.27
    ა
    0.27
    عي
    0.27
    ت
    0.26
    POSITIVE LOGITS
    :
    0.38
    -
    0.32
    g
    0.31
    al
    0.30
    :\\
    0.30
    é
    0.30
    ;
    0.29
     mengh
    0.27
    h
    0.27
     affliction
    0.27
    Act Density 0.209%

    No Known Activations