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

    Neuronpedia

    INDEX
    Explanations

    News reporting context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Henderson
    -0.08
     Syracuse
    -0.07
    _OCCURRED
    -0.07
    (theta
    -0.07
     DataAccess
    -0.06
    _RECEIVED
    -0.06
     sendData
    -0.06
    icho
    -0.06
    .Usuario
    -0.06
    成都
    -0.06
    POSITIVE LOGITS
    .gridy
    0.07
     AP
    0.07
    receiver
    0.07
    赛场
    0.07
    any
    0.06
     steering
    0.06
     packages
    0.06
    保荐
    0.06
    ;amp
    0.06
    invalid
    0.06
    Act Density 0.002%

    No Known Activations