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

    Neuronpedia

    INDEX
    Explanations

    common conversational phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kus
    -0.07
    hexdigest
    -0.06
    entry
    -0.06
    NFL
    -0.06
     obra
    -0.06
    人人
    -0.06
     DPI
    -0.06
     GetHashCode
    -0.06
     kval
    -0.06
    냐
    -0.06
    POSITIVE LOGITS
    callee
    0.07
    Vision
    0.07
     ","↵
    0.07
    '])↵
    0.07
     oxidation
    0.07
    angled
    0.06
     Taylor
    0.06
    ↵↵↵↵↵↵
    0.06
    Tracking
    0.06
     danych
    0.06
    Act Density 0.027%

    No Known Activations