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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meisten
    -0.09
    tragung
    -0.08
    qlar
    -0.08
    보기
    -0.08
    Term
    -0.08
     Adj
    -0.08
    Samples
    -0.07
    abbing
    -0.07
    stairs
    -0.07
    的是
    -0.07
    POSITIVE LOGITS
     publica
    0.08
     sektör
    0.08
     virtues
    0.08
     publique
    0.07
     colorful
    0.07
    ેક્ટ
    0.07
     teng
    0.07
     clientele
    0.07
     publications
    0.07
     kunder
    0.07
    Act Density 0.000%

    No Known Activations