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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )?;↵
    -0.06
    爽
    -0.06
    вар
    -0.06
    -google
    -0.06
    ίες
    -0.05
    (sd
    -0.05
    ена
    -0.05
    _lists
    -0.05
    _migration
    -0.05
     ředitel
    -0.05
    POSITIVE LOGITS
     spiritual
    0.07
     Spiritual
    0.07
     ab
    0.07
     presente
    0.07
    ard
    0.06
     RequestContext
    0.06
     जन
    0.06
     τέ
    0.06
     Equ
    0.06
    .scss
    0.06
    Act Density 0.013%

    No Known Activations