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

    Neuronpedia

    INDEX
    Explanations

    digital assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    রুখ
    1.21
     февра
    1.13
     אור
    1.07
     phía
    1.06
    रुख
    1.03
     havde
    1.00
    រយៈ
    0.99
    राबरी
    0.98
     erstwhile
    0.98
     Seiten
    0.97
    POSITIVE LOGITS
    al
    1.29
    ْم
    1.12
    am
    1.09
    aggi
    1.07
     backstory
    1.06
    وك
    1.06
    olution
    1.04
     čo
    1.03
    ệc
    1.02
    amiento
    1.02
    Act Density 0.000%

    No Known Activations