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

    Neuronpedia

    INDEX
    Explanations

    Modals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ักษ
    -0.07
    attended
    -0.07
     SVC
    -0.07
     wildly
    -0.06
    akov
    -0.06
     attendee
    -0.06
     Mã
    -0.06
     Кол
    -0.06
     Papua
    -0.06
     EA
    -0.06
    POSITIVE LOGITS
     quantity
    0.06
    ypi
    0.06
     oper
    0.06
     speed
    0.06
    Sad
    0.06
    Lin
    0.06
    _pago
    0.06
     Auth
    0.06
    ندية
    0.06
    built
    0.06
    Act Density 0.046%

    No Known Activations