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

    Neuronpedia

    INDEX
    Explanations

    comparison and limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maté
    -0.07
    :',
    -0.07
    eri
    -0.06
    alan
    -0.06
     drugs
    -0.06
     sess
    -0.06
     feedback
    -0.06
     thumbnail
    -0.06
    řev
    -0.06
    Pages
    -0.06
    POSITIVE LOGITS
    -anchor
    0.07
    stringLiteral
    0.07
    	ad
    0.06
    maybe
    0.06
    VersionUID
    0.06
    .enc
    0.06
     Plzeň
    0.06
    коп
    0.06
     일어
    0.06
    .cgColor
    0.06
    Act Density 0.106%

    No Known Activations