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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens (especially in constant or syscall number definitions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Livingston
    -0.07
    .ev
    -0.06
    важ
    -0.06
    .Cloud
    -0.06
    沖
    -0.06
    濟
    -0.06
    	lib
    -0.06
    225
    -0.06
    :])
    -0.06
    ayas
    -0.06
    POSITIVE LOGITS
     Ezra
    0.07
    (serial
    0.07
     newline
    0.07
    .bounds
    0.06
     freshness
    0.06
     consulted
    0.06
     }\
    0.06
     gauche
    0.06
     Jud
    0.06
     ofstream
    0.06
    Act Density 0.024%

    No Known Activations