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

    Neuronpedia

    INDEX
    Explanations

    Execution

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of execution or capital‐punishment terms (e.g. “hanged,” “executed,” “guillotined”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     toi
    -0.07
     eagle
    -0.06
     Diese
    -0.06
     discovery
    -0.06
    兹
    -0.06
    される
    -0.06
    QM
    -0.06
    ิโล
    -0.06
     относят
    -0.06
    Got
    -0.06
    POSITIVE LOGITS
    .ย
    0.07
    министра
    0.07
     نوفمبر
    0.06
     grues
    0.06
     Vladim
    0.06
    UTION
    0.06
     Christina
    0.06
    -Allow
    0.06
    /options
    0.06
    .execSQL
    0.06
    Act Density 0.015%

    No Known Activations