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

    Neuronpedia

    INDEX
    Explanations

    Corporate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utils
    -0.06
     pearls
    -0.06
     THEIR
    -0.06
     adapters
    -0.06
     дис
    -0.06
     deniz
    -0.06
    (UUID
    -0.06
     Hüs
    -0.06
     roller
    -0.06
    	union
    -0.06
    POSITIVE LOGITS
     compromised
    0.08
    Corporate
    0.08
    崇
    0.08
     Corporate
    0.08
     corporate
    0.07
    lak
    0.07
     stem
    0.07
    mav
    0.07
    asmine
    0.07
    ianne
    0.07
    Act Density 0.006%

    No Known Activations