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

    Neuronpedia

    INDEX
    Explanations

    advance

    np_max-act · gemini-2.0-flash

    This neuron detects closing expressions of gratitude—specifically the phrase “thanks in advance.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rainy
    -0.07
    toolbox
    -0.07
    риг
    -0.07
    _append
    -0.06
    _income
    -0.06
    stantiate
    -0.06
     دانشجوی
    -0.06
     міс
    -0.06
     mul
    -0.06
    UIApplicationDelegate
    -0.06
    POSITIVE LOGITS
     機
    0.07
    _normalized
    0.07
    ською
    0.07
    ()}}↵
    0.07
     ""))↵
    0.06
     esc
    0.06
    uong
    0.06
     odst
    0.06
    )));↵
    0.06
    )));↵↵
    0.06
    Act Density 0.002%

    No Known Activations