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

    Neuronpedia

    INDEX
    Explanations

    references to explosions or explosive events

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

    explosion, explodes, explode, exploded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     referenties
    -0.34
    المناصب
    -0.33
    estacks
    -0.32
     Picchu
    -0.32
     ligiloj
    -0.31
     manhã
    -0.30
     חיצוניים
    -0.30
    énario
    -0.29
     basse
    -0.28
     ügy
    -0.28
    POSITIVE LOGITS
     explode
    0.93
     exploding
    0.88
     explosion
    0.85
     explodes
    0.82
    explode
    0.78
     exploded
    0.78
     explo
    0.75
     Explosion
    0.71
     explosive
    0.70
    burst
    0.70
    Act Density 0.060%

    No Known Activations