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

    Neuronpedia

    INDEX
    Explanations

    bubble

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [].
    -0.07
    ANGE
    -0.07
     trustee
    -0.07
     тоб
    -0.06
    licht
    -0.06
     applying
    -0.06
    ابع
    -0.06
     produced
    -0.06
    igrations
    -0.06
    .creator
    -0.06
    POSITIVE LOGITS
    Bubble
    0.09
     всп
    0.07
     bubble
    0.07
    bubble
    0.07
     Bubble
    0.06
    gew
    0.06
     bub
    0.06
     nemá
    0.06
    ?f
    0.06
     geliştir
    0.06
    Act Density 0.001%

    No Known Activations