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

    Neuronpedia

    INDEX
    Explanations

    length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oa
    -0.07
    via
    -0.06
    ovie
    -0.06
    ्तर
    -0.06
     Поч
    -0.06
     alteration
    -0.06
    =rand
    -0.06
    	open
    -0.06
    函
    -0.06
    학
    -0.06
    POSITIVE LOGITS
    ойчив
    0.06
     garnered
    0.06
     injust
    0.06
     méth
    0.06
    dez
    0.06
     Tou
    0.06
     informace
    0.06
     priorities
    0.06
    ildo
    0.06
    oleč
    0.06
    Act Density 0.014%

    No Known Activations