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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    乔
    -0.07
     joe
    -0.07
    cción
    -0.07
     IPL
    -0.07
     jack
    -0.07
     yardım
    -0.07
    conexion
    -0.06
     집
    -0.06
    Female
    -0.06
    吸
    -0.06
    POSITIVE LOGITS
    setData
    0.07
    ,total
    0.07
    zes
    0.07
     methodologies
    0.06
    Workflow
    0.06
    合法
    0.06
    kker
    0.06
     הודעה
    0.06
    paces
    0.06
     다양한
    0.06
    Act Density 0.105%

    No Known Activations