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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _above
    -0.07
    (Constants
    -0.07
    AttributeName
    -0.07
     lbl
    -0.07
     article
    -0.06
    _written
    -0.06
     clarity
    -0.06
     Investigators
    -0.06
    	Client
    -0.06
    Tex
    -0.06
    POSITIVE LOGITS
    Selection
    0.07
    erb
    0.07
     fallback
    0.07
    روب
    0.07
     money
    0.06
     sup
    0.06
     Average
    0.06
    аж
    0.06
    olph
    0.06
     roc
    0.06
    Act Density 0.003%

    No Known Activations