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

    Neuronpedia

    INDEX
    Explanations

    Helen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Helen
    -1.83
    Helen
    -1.63
     HELEN
    -1.11
     Helene
    -0.88
     Helena
    -0.84
    helen
    -0.79
     hel
    -0.64
    Helena
    -0.63
     Helens
    -0.63
     Hel
    -0.45
    POSITIVE LOGITS
    참고
    0.79
    ResumeLayout
    0.78
     TextInputType
    0.74
    OGND
    0.73
    cyklopedia
    0.73
    oa̍t
    0.69
     nakalista
    0.68
     فريبيس
    0.66
     gawas
    0.66
    ViewFeatures
    0.65
    Act Density 0.022%

    No Known Activations