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

    Neuronpedia

    INDEX
    Explanations

    /init

    np_max-act · gemini-2.0-flash

    code relating to device drivers and hardware interfaces.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron strongly activates on the “init” component in include‐path tokens (e.g. the “/init” in “<linux/init.h>”), i.e. it detects references to initialization headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     effic
    -0.07
     resist
    -0.07
     Пет
    -0.07
     EV
    -0.07
     dou
    -0.06
     cihaz
    -0.06
     Glouce
    -0.06
    िजल
    -0.06
    ravel
    -0.06
     Marvel
    -0.06
    POSITIVE LOGITS
    .rstrip
    0.06
    /init
    0.06
    .NUM
    0.06
    argout
    0.06
    َج
    0.06
     tls
    0.06
    RequestId
    0.06
    _quality
    0.06
    datagrid
    0.06
    +[
    0.06
    Act Density 0.000%

    No Known Activations