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

    Neuronpedia

    INDEX
    Explanations

    spray

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filters
    -0.07
     extension
    -0.07
    样
    -0.07
     wages
    -0.07
     Artifact
    -0.06
    pace
    -0.06
     manipulate
    -0.06
     trucks
    -0.06
    樣
    -0.06
     BTS
    -0.06
    POSITIVE LOGITS
    .GPIO
    0.08
    .DataGridViewTriState
    0.07
    (TreeNode
    0.07
     urllib
    0.07
    .getMinutes
    0.06
    (fake
    0.06
    報
    0.06
    航空
    0.06
    狼
    0.06
    .:.:.:.
    0.06
    Act Density 0.001%

    No Known Activations