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

    Neuronpedia

    INDEX
    Explanations

    in a

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of code/configuration filenames or file‐extension tokens (e.g. “build.gradle”) in programming‐help contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    enterprise
    -0.06
    搜索
    -0.06
    查
    -0.06
    訓
    -0.06
    سن
    -0.06
     waiver
    -0.06
    zym
    -0.06
    Reject
    -0.06
     selects
    -0.05
    вест
    -0.05
    POSITIVE LOGITS
     với
    0.07
    ==(
    0.07
    .ce
    0.07
    ifton
    0.07
    alsy
    0.06
    ايت
    0.06
     všichni
    0.06
    orsi
    0.06
    -un
    0.06
    iiii
    0.06
    Act Density 0.023%

    No Known Activations