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

    Neuronpedia

    INDEX
    Explanations

    comparisons and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Has
    -0.07
    [file
    -0.07
     기다
    -0.07
     rolling
    -0.07
    受到
    -0.07
     you
    -0.06
     survive
    -0.06
     raises
    -0.06
    해보
    -0.06
     हल
    -0.06
    POSITIVE LOGITS
    Song
    0.07
    注
    0.07
     limburg
    0.06
     sprite
    0.06
     airspace
    0.06
    enção
    0.06
    REEN
    0.06
    GF
    0.06
     CHAPTER
    0.06
     способом
    0.06
    Act Density 0.132%

    No Known Activations