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

    Neuronpedia

    INDEX
    Explanations

    history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tone
    -0.07
    cap
    -0.06
     Taiwanese
    -0.06
    ilter
    -0.06
     UB
    -0.06
    LOOP
    -0.06
    NSURL
    -0.06
     Liz
    -0.06
    	bs
    -0.06
     údaje
    -0.06
    POSITIVE LOGITS
     -$
    0.06
     жизни
    0.06
     observation
    0.06
     }}/
    0.06
     "..
    0.06
     Early
    0.06
     astounding
    0.06
    amas
    0.06
    -auto
    0.06
    -earth
    0.06
    Act Density 0.025%

    No Known Activations