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

    Neuronpedia

    INDEX
    Explanations

    /dev

    np_max-act · gemini-2.0-flash

    The neuron activates on filesystem path strings (especially absolute paths with drive letters or leading slashes).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    リスト
    -0.07
     HALF
    -0.07
    callbacks
    -0.06
     详情
    -0.06
    .Controllers
    -0.06
    .getActivity
    -0.06
     doz
    -0.06
     以
    -0.06
     District
    -0.06
    .Thread
    -0.06
    POSITIVE LOGITS
     допомаг
    0.07
    -ext
    0.07
     Switzerland
    0.07
     probl
    0.07
    Pas
    0.06
     명
    0.06
    彻
    0.06
     будут
    0.06
     Hampshire
    0.06
     widest
    0.06
    Act Density 0.017%

    No Known Activations