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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash

    The neuron primarily fires on tokens related to error reports and troubleshooting (e.g. “error,” exception names, and diagnostic terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     масло
    -0.07
     Někter
    -0.07
    latlong
    -0.07
     Jou
    -0.07
     죽
    -0.06
     Seç
    -0.06
    gameObject
    -0.06
    肖
    -0.06
     nás
    -0.06
    งเศ
    -0.06
    POSITIVE LOGITS
     appointments
    0.07
     alphabet
    0.07
     quản
    0.06
     bookstore
    0.06
    }.↵
    0.06
    agements
    0.06
    forcing
    0.06
     outside
    0.06
    _UNITS
    0.06
     elect
    0.06
    Act Density 0.030%

    No Known Activations