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

    Neuronpedia

    INDEX
    Explanations

    groups and labels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     result
    -0.52
    wpdb
    -0.48
    @[+][
    -0.48
    u
    -0.47
    ysen
    -0.47
    label
    -0.46
    śmy
    -0.46
     group
    -0.46
    ful
    -0.45
     to
    -0.44
    POSITIVE LOGITS
    ########.
    0.85
    Tikang
    0.84
     Shakspeare
    0.82
    MessageOf
    0.80
    RegressionTest
    0.79
     للمعارف
    0.78
    expandindo
    0.78
    دانشنامهٔ
    0.76
     Administrativna
    0.75
     swears
    0.75
    Act Density 0.226%

    No Known Activations