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

    Neuronpedia

    INDEX
    Explanations

    article links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sewer
    0.41
    铣
    0.38
    𝕄
    0.38
    fourths
    0.37
     machinist
    0.37
     sparsim
    0.37
     kiến
    0.36
    KERN
    0.36
     posicion
    0.36
    仓
    0.36
    POSITIVE LOGITS
     Article
    0.86
     article
    0.76
    Article
    0.76
     Talk
    0.72
    Talk
    0.72
     talk
    0.65
     Artikel
    0.64
     artikel
    0.62
    article
    0.62
     ARTICLE
    0.60
    Act Density 0.000%

    No Known Activations