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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sel
    -0.07
     lowest
    -0.07
    _Profile
    -0.07
     Kate
    -0.06
     Gerry
    -0.06
     surprising
    -0.06
    itol
    -0.06
     plateau
    -0.06
    Imagen
    -0.06
    	lines
    -0.06
    POSITIVE LOGITS
    �
    0.07
    _tA
    0.06
    WebpackPlugin
    0.06
    /options
    0.06
    ++];↵
    0.06
     opat
    0.06
     autonomous
    0.06
     Borough
    0.06
    最新
    0.06
    /operators
    0.05
    Act Density 0.042%

    No Known Activations