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
    .timeline
    -0.07
    athing
    -0.06
     haci
    -0.06
     ख
    -0.06
    Tiles
    -0.06
     hablar
    -0.06
    Раз
    -0.06
    (radius
    -0.06
     katı
    -0.06
     wollte
    -0.06
    POSITIVE LOGITS
    また
    0.07
    ()↵
    0.07
     Auburn
    0.07
    (",")↵
    0.07
     �
    0.07
     北
    0.06
     UICollectionView
    0.06
     IDictionary
    0.06
     ensl
    0.06
     ###↵
    0.06
    Act Density 0.027%

    No Known Activations