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

    Neuronpedia

    INDEX
    Explanations

    Code/Math

    np_max-act · gemini-2.0-flash

    This neuron responds to the object‐member access operator (“->”) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    widgets
    -0.07
     особлив
    -0.07
     scn
    -0.07
    َن
    -0.07
     igual
    -0.07
     '>
    -0.06
    ických
    -0.06
    stu
    -0.06
     طريق
    -0.06
     teknik
    -0.06
    POSITIVE LOGITS
    unteer
    0.09
    Faculty
    0.07
    _ec
    0.07
    European
    0.06
    /dd
    0.06
     gamble
    0.06
    _MY
    0.06
    Foreign
    0.06
    publisher
    0.06
    当前
    0.06
    Act Density 0.226%

    No Known Activations