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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on numeric literals—especially floating‐point constants—in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     heartbeat
    -0.06
    شنبه
    -0.06
     biologist
    -0.06
     механи
    -0.06
     consideration
    -0.06
     liter
    -0.06
     Zen
    -0.06
     Fle
    -0.06
    verification
    -0.06
    pts
    -0.06
    POSITIVE LOGITS
     거
    0.08
     livest
    0.07
    W
    0.06
    _aw
    0.06
     данны
    0.06
     подіб
    0.06
     geral
    0.06
    .places
    0.06
    lopedia
    0.06
    0.06
    Act Density 0.096%

    No Known Activations