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

    Neuronpedia

    INDEX
    Explanations

    escape

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of characters escaping or narrowly evading peril.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    subscription
    -0.07
    Topics
    -0.06
     Walton
    -0.06
    enaire
    -0.06
    update
    -0.06
    closing
    -0.06
    커
    -0.06
     toàn
    -0.06
     muh
    -0.06
     Luis
    -0.06
    POSITIVE LOGITS
    iber
    0.07
    etically
    0.07
    --}}↵
    0.07
     Antarctica
    0.07
     numberWithInt
    0.06
    нение
    0.06
     профилакти
    0.06
     suppressed
    0.06
     ''
    0.06
    endencies
    0.06
    Act Density 0.015%

    No Known Activations