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

    Neuronpedia

    INDEX
    Explanations

    acknowledgments through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nghìn
    -0.08
     لم
    -0.08
     Lonely
    -0.07
    豨
    -0.07
     luck
    -0.07
    mov
    -0.07
     автомобиль
    -0.07
    <Address
    -0.07
    那个时候
    -0.07
     Luck
    -0.07
    POSITIVE LOGITS
    relay
    0.08
    .quiz
    0.07
    燃烧
    0.07
    Cookies
    0.07
     Colombia
    0.07
     Starts
    0.07
    הגנה
    0.07
    Hunter
    0.07
    Browse
    0.07
    —they
    0.06
    Act Density 0.001%

    No Known Activations