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

    Neuronpedia

    INDEX
    Explanations

    warnings and precautions related to safety and health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    fire, heat, sparks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.58
    tvguidetime
    -0.52
    
    -0.51
    ถม
    -0.50
    Tembelea
    -0.50
    archiviato
    -0.48
    ropriate
    -0.48
    磅
    -0.47
    Cyfarwyddwr
    -0.46
     Paglinawan
    -0.46
    POSITIVE LOGITS
     ignition
    0.45
     Ignition
    0.38
    Obrázky
    0.37
     sparks
    0.32
    Ignition
    0.32
     ignited
    0.31
     flames
    0.31
    spark
    0.30
    lässlich
    0.30
     fire
    0.29
    Act Density 0.002%

    No Known Activations