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

    Neuronpedia

    INDEX
    Explanations

    pattern-matching chatbots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lands
    -0.08
     violin
    -0.08
     glyph
    -0.08
    溪
    -0.08
     portrait
    -0.08
     UX
    -0.08
    Glyph
    -0.07
     creamy
    -0.07
     کر
    -0.07
    誰
    -0.07
    POSITIVE LOGITS
     ответы
    0.11
    answers
    0.10
    Responses
    0.09
     respuestas
    0.09
     stuffing
    0.09
     Responses
    0.09
     antigos
    0.09
     antiguos
    0.09
     Antworten
    0.09
    返信
    0.09
    Act Density 0.002%

    No Known Activations