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

    Neuronpedia

    INDEX
    Explanations

    data types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _image
    -0.07
     Ish
    -0.07
     vox
    -0.07
     nebyl
    -0.07
    (Xml
    -0.07
    Spi
    -0.07
     Seth
    -0.07
     Alley
    -0.07
     purchaser
    -0.06
     Brush
    -0.06
    POSITIVE LOGITS
     NAN
    0.07
    -care
    0.07
     bid
    0.06
     boolean
    0.06
     navigationOptions
    0.06
    :String
    0.06
    専
    0.06
    ,out
    0.06
    .Encode
    0.06
    queueReusable
    0.06
    Act Density 0.029%

    No Known Activations