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

    Neuronpedia

    INDEX
    Explanations

    adapt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    239
    -0.07
    -form
    -0.06
     vé
    -0.06
     является
    -0.06
    awy
    -0.06
    897
    -0.06
    ibilities
    -0.06
     remarked
    -0.06
    ALCHEMY
    -0.06
     hesab
    -0.06
    POSITIVE LOGITS
     LENG
    0.07
    екс
    0.07
    sha
    0.06
     advisory
    0.06
    .fixed
    0.06
     adap
    0.06
    .Right
    0.06
    icao
    0.06
    	sf
    0.06
     isn
    0.06
    Act Density 0.008%

    No Known Activations