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

    Neuronpedia

    INDEX
    Explanations

    name and entity prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     സംഭവ
    0.49
     GLS
    0.46
    êtes
    0.44
    ியுடன்
    0.43
     ውስ
    0.42
    ดื่ม
    0.41
     دنیا
    0.40
    rentes
    0.40
    epine
    0.40
    ត្រូវការ
    0.40
    POSITIVE LOGITS
     bill
    0.93
     Bill
    0.87
    bill
    0.84
    Bill
    0.82
     BILL
    0.80
     bills
    0.77
     Bills
    0.77
    Bills
    0.76
     Bil
    0.74
     बिल
    0.73
    Act Density 0.008%

    No Known Activations