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

    Neuronpedia

    INDEX
    Explanations

    spectral density

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    beautiful
    -0.08
     proof
    -0.07
    Wheel
    -0.07
    振り
    -0.07
    倏
    -0.07
    怔
    -0.07
    comparison
    -0.07
    اعتم
    -0.07
    慵
    -0.07
    嘴角
    -0.07
    POSITIVE LOGITS
    sterdam
    0.07
    *log
    0.07
    נוסע
    0.07
    water
    0.07
     Billing
    0.06
    direccion
    0.06
    igest
    0.06
    讀取
    0.06
    ísticas
    0.06
    Enabled
    0.06
    Act Density 0.012%

    No Known Activations