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

    Neuronpedia

    INDEX
    Explanations

    Java code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    播放
    -0.07
     constituted
    -0.07
     recipe
    -0.07
    (TEXT
    -0.07
    ä
    -0.07
    -graph
    -0.07
    Singleton
    -0.06
     layers
    -0.06
     R
    -0.06
     swaps
    -0.06
    POSITIVE LOGITS
    alling
    0.06
    .DataVisualization
    0.06
    .barDockControl
    0.06
     LogManager
    0.06
    ánd
    0.06
    wealth
    0.06
    Mount
    0.06
     مؤس
    0.06
     numberWithInt
    0.06
     jaz
    0.06
    Act Density 0.005%

    No Known Activations