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

    Neuronpedia

    INDEX
    Explanations

    Programming code and data

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literal tokens—especially floating‐point numbers—wherever they appear in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    literal
    -0.08
    titulo
    -0.07
    .abstract
    -0.07
    ५
    -0.07
    arda
    -0.07
     Gat
    -0.06
    Space
    -0.06
    .Fl
    -0.06
     Raptors
    -0.06
     %}↵
    -0.06
    POSITIVE LOGITS
    INGTON
    0.06
    ملة
    0.06
     landing
    0.06
     li
    0.06
     catast
    0.06
    ेब
    0.06
    earning
    0.06
     threatens
    0.06
    変
    0.06
     getPosition
    0.05
    Act Density 0.014%

    No Known Activations