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

    Neuronpedia

    INDEX
    Explanations

    normal and expected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cour
    0.40
    0.40
    says
    0.38
     mandala
    0.37
     माया
    0.37
     वैष्ण
    0.37
    Required
    0.37
     रहेंगे
    0.37
     कैशबैक
    0.37
    呆
    0.37
    POSITIVE LOGITS
     Го
    0.40
     સામાન્ય
    0.40
     عادي
    0.39
     Gö
    0.38
     обы
    0.38
     angl
    0.38
     سائٹ
    0.37
     normalen
    0.36
     κό
    0.36
     Et
    0.36
    Act Density 0.000%

    No Known Activations