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

    Neuronpedia

    INDEX
    Explanations

    eye movements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Map
    -0.07
     Sem
    -0.07
    到达
    -0.07
     Convert
    -0.07
     Adv
    -0.07
     nef
    -0.07
     mại
    -0.07
     Selling
    -0.07
     Gui
    -0.07
     consecutive
    -0.07
    POSITIVE LOGITS
    كا
    0.07
    phil
    0.07
    _pause
    0.07
    ILogger
    0.07
    🎨
    0.07
     antlr
    0.07
    뗌
    0.06
     �
    0.06
    라
    0.06
    BackgroundColor
    0.06
    Act Density 0.005%

    No Known Activations