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

    Neuronpedia

    INDEX
    Explanations

    code, technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.88
    -0.84
     autorytatywna
    -0.80
    AccessorTable
    -0.79
    enderror
    -0.76
    istoitu
    -0.75
    GEBURTSDATUM
    -0.74
     дописавши
    -0.74
    AddTagHelper
    -0.73
    ">:
    -0.72
    POSITIVE LOGITS
    訊
    0.54
    גי
    0.51
     as
    0.47
     cí
    0.46
     «
    0.46
     Bol
    0.46
     frequenza
    0.45
     Auto
    0.45
     couver
    0.45
    [^
    0.44
    Act Density 0.002%

    No Known Activations