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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron responds to the special end‐of‐turn/end‐of‐text marker tokens (e.g. the “<|eot_id|>” tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    lname
    -0.06
     lyr
    -0.06
    	effect
    -0.06
     Prostit
    -0.06
    申博
    -0.06
    ":{"
    -0.06
    şiv
    -0.06
    Otherwise
    -0.06
    -|
    -0.06
    เฟ
    -0.06
    POSITIVE LOGITS
    주
    0.07
     thirds
    0.07
    (theta
    0.07
    òa
    0.07
     coping
    0.07
    向
    0.07
    DataContext
    0.06
    ’↵↵
    0.06
     oats
    0.06
    VK
    0.06
    Act Density 0.024%

    No Known Activations