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

    Neuronpedia

    INDEX
    Explanations

    diagrams of relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.63
    ה
    0.63
    ندي
    0.52
     সমালো
    0.52
    cji
    0.49
    كي
    0.49
    يد
    0.49
    но
    0.49
    ريكية
    0.48
    Colleg
    0.47
    POSITIVE LOGITS
    getFlight
    0.47
     Shores
    0.46
    inei
    0.45
     anthropological
    0.45
    લિક
    0.44
    arius
    0.44
     কারন
    0.44
     आना
    0.44
     Adriatic
    0.44
    的情况下
    0.43
    Act Density 0.000%

    No Known Activations