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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash

    The neuron activates on OS/architecture specifier tokens (e.g. linux/amd64, windows/386, arm64, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    一个人
    -0.07
    酒店
    -0.07
    XYZ
    -0.07
    妮
    -0.07
    /R
    -0.06
     belly
    -0.06
     Devices
    -0.06
     choked
    -0.06
    ツ
    -0.06
     remembered
    -0.06
    POSITIVE LOGITS
    แนะ
    0.07
    som
    0.07
    Authorization
    0.07
    گو
    0.06
     ostream
    0.06
    _sensor
    0.06
     adhere
    0.06
     Twe
    0.06
    奖
    0.06
     naw
    0.06
    Act Density 0.014%

    No Known Activations