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

    Neuronpedia

    INDEX
    Explanations

    User testing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     生
    -0.08
    punk
    -0.07
    ochastic
    -0.07
    Green
    -0.07
    ookies
    -0.07
    _read
    -0.07
     compelled
    -0.07
    🏯
    -0.07
    Hung
    -0.07
    annels
    -0.06
    POSITIVE LOGITS
    .addSubview
    0.07
    蚜
    0.07
     GUIDE
    0.07
     Rihanna
    0.07
     Fac
    0.07
     tenía
    0.07
    Clr
    0.07
     있지
    0.07
     lack
    0.06
    略微
    0.06
    Act Density 0.032%

    No Known Activations