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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UIApplication
    -0.08
    ’ét
    -0.07
     건
    -0.07
    _agent
    -0.07
    abilecek
    -0.07
    racak
    -0.06
    .drawText
    -0.06
    眼
    -0.06
    END
    -0.06
    َت
    -0.06
    POSITIVE LOGITS
    amping
    0.06
     addicted
    0.06
    lední
    0.06
     setUsername
    0.06
    _;↵
    0.06
    bine
    0.06
    ch
    0.06
    OLOR
    0.06
    _ak
    0.06
     belong
    0.06
    Act Density 0.014%

    No Known Activations