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

    Neuronpedia

    INDEX
    Explanations

    statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bool
    -0.06
     }}"↵
    -0.06
    	NSString
    -0.06
    bcm
    -0.06
     reminiscent
    -0.06
    Beans
    -0.06
    arpa
    -0.06
    Printer
    -0.06
     kır
    -0.06
     metre
    -0.06
    POSITIVE LOGITS
     cave
    0.08
     Rel
    0.07
    umption
    0.07
     swim
    0.06
     debate
    0.06
     Buffy
    0.06
    결
    0.06
    ishment
    0.06
    ATRIX
    0.06
     entreprise
    0.06
    Act Density 0.005%

    No Known Activations