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

    Neuronpedia

    INDEX
    Explanations

    charge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     파
    -0.07
     فرو
    -0.06
     BaseModel
    -0.06
     バ
    -0.06
    ็จพระ
    -0.06
     kn
    -0.06
     raspberry
    -0.06
     �
    -0.06
     penned
    -0.06
    784
    -0.06
    POSITIVE LOGITS
     Hin
    0.07
     immigrant
    0.07
    acja
    0.07
    adě
    0.07
    Neither
    0.07
     chơi
    0.07
    .cart
    0.07
    (argv
    0.07
    оти
    0.06
    >'.$
    0.06
    Act Density 0.000%

    No Known Activations