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

    Neuronpedia

    INDEX
    Explanations

    means

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     internetowa
    -0.41
     fers
    -0.41
     tungkol
    -0.40
    DOCTYPE
    -0.40
    არი
    -0.39
     cref
    -0.38
    Initializable
    -0.38
    herself
    -0.37
    CES
    -0.36
     expanded
    -0.36
    POSITIVE LOGITS
     that
    0.81
     it
    0.75
    twimg
    0.74
    NamedQueries
    0.74
    AddHtmlAttribute
    0.73
     whoever
    0.71
     समीक्षक
    0.70
     he
    0.69
     whome
    0.69
     I
    0.69
    Act Density 0.004%

    No Known Activations