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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    This neuron detects identifier tokens that begin with “use” or “with,” such as useClass, useForm, or withObjectPHIDs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .RequestMethod
    -0.07
     люб
    -0.07
    AssignableFrom
    -0.07
    กระท
    -0.07
     vậy
    -0.07
    .hstack
    -0.06
    equalTo
    -0.06
     Depends
    -0.06
     "=
    -0.06
    จาก
    -0.06
    POSITIVE LOGITS
    (flags
    0.07
    Ａ
    0.07
     lust
    0.07
     dead
    0.07
     sports
    0.06
     submenu
    0.06
    _SEGMENT
    0.06
     Tree
    0.06
     mines
    0.06
     register
    0.06
    Act Density 0.041%

    No Known Activations