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

    Neuronpedia

    INDEX
    Explanations

    informational texts

    np_max-act · gemini-2.0-flash

    This neuron detects references to quantitative data or statistical terms (e.g., sales figures, percentages, market statistics).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    aky
    -0.07
    typing
    -0.06
     ارزیابی
    -0.06
    :::::::::::::
    -0.06
    IfNeeded
    -0.06
     Frozen
    -0.06
    ()]
    -0.06
    agree
    -0.06
    لام
    -0.06
     infra
    -0.06
    POSITIVE LOGITS
    _BOUNDS
    0.07
    мест
    0.06
    ้งาน
    0.06
     flirt
    0.06
    wechat
    0.06
    ดำ
    0.06
    _PACKET
    0.06
    .temperature
    0.06
    режд
    0.06
     HE
    0.06
    Act Density 0.067%

    No Known Activations