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

    Neuronpedia

    INDEX
    Explanations

    opportunities and support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    013
    -0.07
    müştür
    -0.07
    :@""
    -0.07
     emoji
    -0.07
    Studio
    -0.07
    279
    -0.06
    034
    -0.06
     satire
    -0.06
    Mais
    -0.06
    267
    -0.06
    POSITIVE LOGITS
     Rune
    0.06
    arium
    0.06
    return
    0.06
    -прав
    0.06
     Щ
    0.06
     Quotes
    0.06
    enschaft
    0.06
    ierung
    0.06
     lục
    0.06
    charging
    0.06
    Act Density 0.336%

    No Known Activations