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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tember
    -0.07
    norm
    -0.07
    xp
    -0.07
    pecified
    -0.07
    gence
    -0.06
    翔
    -0.06
    erap
    -0.06
     Fraser
    -0.06
    وسی
    -0.06
     Regina
    -0.06
    POSITIVE LOGITS
     […]↵↵
    0.07
     Multi
    0.07
    UE
    0.07
     quick
    0.07
    055
    0.06
     Hentai
    0.06
    _SEGMENT
    0.06
    	before
    0.06
     misunderstood
    0.06
    _reader
    0.06
    Act Density 0.023%

    No Known Activations