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

    Neuronpedia

    INDEX
    Explanations

    remove/disable

    np_max-act · gemini-2.0-flash

    This neuron activates on code tokens that signal teardown or cleanup actions—specifically function or method names like “remove” and “disable.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    programming constructs related to software licensing and copyright information.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Severity
    -0.07
    mapped
    -0.07
    초
    -0.06
    configs
    -0.06
     apocalypse
    -0.06
    ptides
    -0.06
    enic
    -0.06
    _alarm
    -0.06
    lane
    -0.06
    CTL
    -0.06
    POSITIVE LOGITS
     �
    0.07
     Ec
    0.07
    ,error
    0.06
    生
    0.06
     pornofil
    0.06
     Quadr
    0.06
     Mits
    0.06
     выращи
    0.06
     imaginative
    0.06
    Leod
    0.06
    Act Density 0.016%

    No Known Activations