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

    Neuronpedia

    INDEX
    Explanations

    hyphens, periods, numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Betty
    -0.07
    ตำบล
    -0.07
     dem
    -0.07
     ett
    -0.07
     Wendy
    -0.06
     Bennett
    -0.06
     deterior
    -0.06
     nurs
    -0.06
     templ
    -0.06
     Lou
    -0.06
    POSITIVE LOGITS
     inhibitor
    0.07
     Uz
    0.07
     actualizar
    0.07
     Од
    0.06
    -Version
    0.06
    Participant
    0.06
     niż
    0.06
    cdf
    0.06
     czas
    0.06
    	RTLU
    0.06
    Act Density 0.063%

    No Known Activations