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

    Neuronpedia

    INDEX
    Explanations

    tools and self-defense

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of self-defense tools or weapons.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _finder
    -0.07
     Pelosi
    -0.06
    _align
    -0.06
     Incontri
    -0.06
    ACHINE
    -0.06
    -slide
    -0.06
     schöne
    -0.06
    乙
    -0.06
    apture
    -0.06
    utto
    -0.06
    POSITIVE LOGITS
    icator
    0.07
     deploying
    0.06
     ByteArrayInputStream
    0.06
    comboBox
    0.06
    etest
    0.06
     lorem
    0.06
     Documentary
    0.06
    �
    0.06
     bolest
    0.06
    (IService
    0.06
    Act Density 0.010%

    No Known Activations