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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expandindo
    -0.78
     مشين
    -0.77
    WebVitals
    -0.75
     kaynağından
    -0.75
    AndEndTag
    -0.71
     <=",
    -0.71
     kasarigan
    -0.70
     MainAxisSize
    -0.70
    UrlResolution
    -0.68
     TextAppearance
    -0.66
    POSITIVE LOGITS
    '
    0.50
     rock
    0.45
    ’
    0.45
     wanna
    0.45
     
    0.45
    duğu
    0.44
     trovano
    0.42
    DEFIN
    0.42
    wanna
    0.42
     nggak
    0.42
    Act Density 0.017%

    No Known Activations