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

    Neuronpedia

    INDEX
    Explanations

    question words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     salvage
    -0.08
    -0.07
     Instructions
    -0.07
    abet
    -0.07
     needing
    -0.07
    саж
    -0.07
     instructions
    -0.07
     ))
    -0.07
     remainder
    -0.07
    ™
    -0.07
    POSITIVE LOGITS
    favorite
    0.10
     perceptions
    0.09
    Favorite
    0.09
     favoriete
    0.09
     Какие
    0.09
     favourite
    0.09
    최근
    0.09
    有没有
    0.08
     motivations
    0.08
     favorite
    0.08
    Act Density 0.047%
    No Known Activations