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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    算
    -0.07
    issent
    -0.07
     schl
    -0.07
    _refptr
    -0.07
    奇特
    -0.07
    ảy
    -0.07
     grou
    -0.07
     owes
    -0.07
     purification
    -0.06
     Appeal
    -0.06
    POSITIVE LOGITS
     [[
    0.07
    (chan
    0.07
    CustomLabel
    0.06
     capacitor
    0.06
    换句话
    0.06
    LEG
    0.06
     במקרה
    0.06
     AM
    0.06
    [E
    0.06
     Setter
    0.06
    Act Density 0.004%

    No Known Activations