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

    Neuronpedia

    INDEX
    Explanations

    Code enums

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literal tokens (e.g. integer or floating‐point constants) in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ὐ
    -0.07
     Junction
    -0.07
    .UseText
    -0.07
    ská
    -0.06
    application
    -0.06
    adata
    -0.06
     Mer
    -0.06
    icrous
    -0.06
    GetProperty
    -0.06
     선거
    -0.06
    POSITIVE LOGITS
     %#
    0.07
    Apps
    0.06
    fires
    0.06
    .setToolTipText
    0.06
    jících
    0.06
    ','$
    0.06
    òng
    0.06
    .http
    0.06
    搞
    0.06
    (abs
    0.06
    Act Density 0.012%

    No Known Activations