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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    The neuron detects the “*” markers used at the start of lines in block‐comment license headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _extend
    -0.07
     excl
    -0.07
    orest
    -0.07
    글
    -0.07
    Ст
    -0.06
    proper
    -0.06
    Excel
    -0.06
    _locator
    -0.06
    Van
    -0.06
    евер
    -0.06
    POSITIVE LOGITS
     grievances
    0.07
    _vendor
    0.06
     Griff
    0.06
    _MESSAGE
    0.06
    .findIndex
    0.06
    .capitalize
    0.06
    �
    0.06
     bombed
    0.06
    dım
    0.06
     referral
    0.06
    Act Density 0.011%

    No Known Activations