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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash

    The neuron detects numeric literal tokens—especially floating‐point numbers—in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Macron
    -0.06
    ीद
    -0.06
    orang
    -0.06
    Nb
    -0.06
    材料
    -0.06
     loot
    -0.06
    oleans
    -0.06
     Mad
    -0.06
    ANCH
    -0.06
    amics
    -0.06
    POSITIVE LOGITS
     začala
    0.07
     terra
    0.07
     grown
    0.07
     sensed
    0.06
     destin
    0.06
     виробництва
    0.06
    .screen
    0.06
     ocor
    0.06
     přest
    0.06
     idade
    0.06
    Act Density 0.017%

    No Known Activations