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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of “key” (especially in crypto‐related identifiers like Key, key_schedule, etc.), flagging references to cryptographic key setup or scheduling.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ivariate
    -0.07
     gez
    -0.07
    Mont
    -0.07
    ","+
    -0.06
    girls
    -0.06
     componentName
    -0.06
    avax
    -0.06
    agher
    -0.06
    -turned
    -0.06
    /admin
    -0.06
    POSITIVE LOGITS
     Saving
    0.07
    cia
    0.07
    �
    0.07
    bek
    0.07
     Especially
    0.06
     packed
    0.06
     Ensure
    0.06
     SR
    0.06
    ตา
    0.06
     Specialists
    0.06
    Act Density 0.007%

    No Known Activations