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

    Neuronpedia

    INDEX
    Explanations

    Deserializing objects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Timer
    -0.07
     حر
    -0.07
     Output
    -0.06
     repeated
    -0.06
    iado
    -0.06
    placer
    -0.06
    criptions
    -0.06
     continuous
    -0.06
    inals
    -0.06
     fraudulent
    -0.06
    POSITIVE LOGITS
     रख
    0.07
     béné
    0.07
    UIApplicationDelegate
    0.07
     خانو
    0.06
     sexdate
    0.06
     nive
    0.06
     olanak
    0.06
     Japon
    0.06
     şirket
    0.06
    ไฟฟ
    0.06
    Act Density 0.024%

    No Known Activations