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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    702
    -0.07
    leave
    -0.07
    .azure
    -0.06
    ी-
    -0.06
    prov
    -0.06
    folder
    -0.06
     луч
    -0.06
     Quar
    -0.06
    인증
    -0.06
    .grade
    -0.06
    POSITIVE LOGITS
    (string
    0.07
     για
    0.06
    ктів
    0.06
    Якщо
    0.06
    URRENCY
    0.06
     error
    0.06
    ΕΧ
    0.06
     lept
    0.06
    	export
    0.06
     boş
    0.06
    Act Density 0.002%

    No Known Activations