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

    Neuronpedia

    INDEX
    Explanations

    ./

    np_max-act · gemini-2.0-flash

    The neuron detects module‐import paths in CommonJS require calls.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ￣￣
    -0.07
     수
    -0.06
    licant
    -0.06
     SubLObject
    -0.06
    SOEVER
    -0.06
     RadioButton
    -0.06
     msgstr
    -0.06
    _RS
    -0.06
    ching
    -0.06
    ání
    -0.06
    POSITIVE LOGITS
     kent
    0.07
     ${
    0.07
    _Is
    0.06
     específ
    0.06
     multif
    0.06
     컨
    0.06
     con
    0.06
     phy
    0.06
     heavily
    0.06
     Paula
    0.06
    Act Density 0.002%

    No Known Activations