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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron detects programming-related control‐flow and event‐handling keywords (for example “event,” “click,” “Switch,” “case,” “goto,” and “loop”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    áng
    -0.07
    loads
    -0.07
     Urban
    -0.06
     湖
    -0.06
     dorm
    -0.06
     Microsoft
    -0.06
     sorted
    -0.06
    precision
    -0.06
     —
    -0.06
    Fee
    -0.06
    POSITIVE LOGITS
    oralType
    0.08
     UITapGestureRecognizer
    0.07
     hbox
    0.06
     TextView
    0.06
    _decorator
    0.06
    cmpeq
    0.06
     jMenuItem
    0.06
    lesai
    0.06
     roleId
    0.06
    .updateDynamic
    0.06
    Act Density 0.110%

    No Known Activations