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

    Neuronpedia

    INDEX
    Explanations

    Each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dest
    -0.08
    ဟ
    -0.07
    🐸
    -0.07
     condolences
    -0.07
    ✽
    -0.07
    .DrawString
    -0.07
    扫一扫
    -0.07
     UserType
    -0.07
     Karen
    -0.07
     부분
    -0.07
    POSITIVE LOGITS
     planners
    0.07
    _prod
    0.07
     observational
    0.07
    navigator
    0.07
     architectural
    0.07
    etal
    0.06
    _attached
    0.06
     cultivated
    0.06
     Writers
    0.06
    Measured
    0.06
    Act Density 0.032%

    No Known Activations