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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     posto
    -0.07
    레벨
    -0.07
    xdb
    -0.07
    .guid
    -0.06
    .getDocument
    -0.06
    inst
    -0.06
     曰
    -0.06
     comando
    -0.06
    スタ
    -0.06
    	doc
    -0.06
    POSITIVE LOGITS
     Hulk
    0.08
    :The
    0.06
    OLS
    0.06
     Slam
    0.06
     versatility
    0.06
     contamination
    0.06
    ráž
    0.06
     downstairs
    0.06
    ummings
    0.06
    uffle
    0.06
    Act Density 0.005%

    No Known Activations