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

    Neuronpedia

    INDEX
    Explanations

    labeled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     label
    -2.33
     labeled
    -2.09
    label
    -2.06
     labelled
    -2.06
     Label
    -1.95
     labeling
    -1.88
    labeled
    -1.86
     labelling
    -1.86
     labels
    -1.82
    Label
    -1.80
    POSITIVE LOGITS
    er
    0.74
    led
    0.67
    ing
    0.63
    DoubleQuotes
    0.50
    t
    0.46
    ed
    0.45
     with
    0.45
    da
    0.45
     ed
    0.44
    ER
    0.44
    Act Density 0.117%

    No Known Activations