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

    Neuronpedia

    INDEX
    Explanations

    references to physical harm or damage

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

    harm or damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➊
    -0.50
    BeforeClass
    -0.49
     îns
    -0.48
     libremente
    -0.48
    SpringRunner
    -0.47
    }{*}{
    -0.47
    nikom
    -0.46
    rolid
    -0.46
    thoven
    -0.45
    Vezi
    -0.44
    POSITIVE LOGITS
     Damage
    1.29
    damage
    1.20
    Damage
    1.20
     DAMAGE
    1.16
     damage
    1.15
     Damaged
    1.02
    DAMAGE
    1.00
    damaged
    0.98
     damaged
    0.96
     Damages
    0.95
    Act Density 0.018%

    No Known Activations