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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron flags lines stating forum permission errors (e.g. “You cannot reply to topics,” “cannot post new topics,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     theories
    -0.07
    ‌ها
    -0.06
     typical
    -0.06
     행동
    -0.06
     panorama
    -0.06
     TRACK
    -0.06
    TAIL
    -0.06
     stories
    -0.06
    这
    -0.06
    dyž
    -0.06
    POSITIVE LOGITS
     applauded
    0.07
    ...");↵↵
    0.06
    .info
    0.06
    	labels
    0.06
     relinqu
    0.06
     tel
    0.06
     */
↵
↵
↵
    0.06
     termination
    0.06
     shopper
    0.06
     juste
    0.06
    Act Density 0.001%

    No Known Activations