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

    Neuronpedia

    INDEX
    Explanations

    executing programs

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to invoking or running external programs (e.g., subprocess or process‐execution contexts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     inhibitor
    -0.08
     IAM
    -0.07
     adjud
    -0.07
    될
    -0.07
     squeezing
    -0.07
    =@
    -0.07
     некотор
    -0.06
     спрос
    -0.06
     tors
    -0.06
    ertos
    -0.06
    POSITIVE LOGITS
    _typeof
    0.06
    ่วมก
    0.06
     vyu
    0.06
     사람
    0.06
     admittedly
    0.06
     theme
    0.06
     gruesome
    0.06
    軟
    0.06
    expense
    0.06
    _^(
    0.06
    Act Density 0.027%

    No Known Activations