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

    Neuronpedia

    INDEX
    Explanations

    2 or 3

    np_max-act · gemini-2.0-flash

    This neuron detects standalone small integer literals (like “2” or “3”) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    hd
    -0.06
     Фор
    -0.06
     nominate
    -0.06
     зд
    -0.06
     مح
    -0.06
     Welt
    -0.06
     Baxter
    -0.06
    -bl
    -0.06
    [max
    -0.06
    िध
    -0.06
    POSITIVE LOGITS
    Router
    0.08
    edException
    0.06
    RAFT
    0.06
    Trigger
    0.06
    compression
    0.06
     TPM
    0.06
     gdy
    0.06
     others
    0.06
     DPI
    0.06
     الإ
    0.06
    Act Density 0.050%

    No Known Activations