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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash

    The neuron fires on the opening square bracket token (“[”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Commons
    -0.06
     nozzle
    -0.06
     commanded
    -0.06
    �
    -0.06
    �p
    -0.06
    ＼:
    -0.06
    δει
    -0.06
     loosen
    -0.06
     tactical
    -0.06
     violent
    -0.06
    POSITIVE LOGITS
    metadata
    0.08
    ""↵
    0.07
    ').↵
    0.07
    .shape
    0.07
    */
↵
    0.07
     uncertainty
    0.07
     adel
    0.07
    ertainty
    0.07
    >"↵
    0.07
    '↵
    0.06
    Act Density 0.009%

    No Known Activations