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

    Neuronpedia

    INDEX
    Explanations

    programming/debugging

    np_max-act · gemini-2.0-flash

    The neuron fires on discussion of resetting or clearing state (e.g. words like “resets,” “reset,” “flush”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     welt
    -0.07
     mostrar
    -0.07
    Asian
    -0.06
    Ocean
    -0.06
     LAS
    -0.06
    رح
    -0.06
    beer
    -0.06
    imation
    -0.06
    рем
    -0.06
     Cabinets
    -0.06
    POSITIVE LOGITS
     jazy
    0.06
    ισμού
    0.06
     vt
    0.06
    ユ
    0.06
    ाहरण
    0.06
     Step
    0.06
    赵
    0.06
     المللی
    0.06
    배송
    0.06
    Ï
    0.06
    Act Density 0.012%

    No Known Activations