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

    Neuronpedia

    INDEX
    Explanations

    Formal writing snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .just
    -0.09
     varying
    -0.07
    肌肉
    -0.07
    --↵
    -0.07
     inter
    -0.07
    led
    -0.07
    衽
    -0.07
     disparities
    -0.07
     ley
    -0.07
    Fields
    -0.07
    POSITIVE LOGITS
    ookeeper
    0.07
    boolean
    0.07
     Furthermore
    0.07
    Ef
    0.06
     companion
    0.06
    hhh
    0.06
     pożycz
    0.06
     endeavour
    0.06
    	main
    0.06
    ☛
    0.06
    Act Density 0.847%

    No Known Activations