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

    Neuronpedia

    INDEX
    Explanations

    available resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ificato
    0.49
     ব্যাটিং
    0.43
    ég
    0.41
    älle
    0.40
     Grave
    0.40
    বেশী
    0.40
    Segoe
    0.38
     बल्लेबाज
    0.38
    ूपी
    0.38
    Example
    0.37
    POSITIVE LOGITS
     abandonar
    0.41
     monoxide
    0.41
     मिळाली
    0.39
    $'
    0.38
    ?"
    0.38
     ২০১১
    0.38
    *"
    0.36
    ,"
    0.36
     الحال
    0.36
     relax
    0.36
    Act Density 0.000%

    No Known Activations