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

    Neuronpedia

    INDEX
    Explanations

    kill

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “kill” (and related process‐termination) commands.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    EditMode
    -0.07
    xaf
    -0.07
     항
    -0.07
    (generator
    -0.07
     персп
    -0.06
    ờ
    -0.06
    .HttpServletResponse
    -0.06
    eni
    -0.06
    [mid
    -0.06
    unda
    -0.06
    POSITIVE LOGITS
     rooted
    0.07
     jednotlivých
    0.07
     grues
    0.07
    (SE
    0.06
    èles
    0.06
     وزار
    0.06
     Puppy
    0.06
     Pins
    0.06
     allocation
    0.06
     compensated
    0.06
    Act Density 0.003%

    No Known Activations