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

    Neuronpedia

    INDEX
    Explanations

    terms related to damage and harm

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

    "damage"

    np_acts-logits-general · gemini-2.0-flash

    damage to systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fallu
    -0.60
    Према
    -0.54
    quels
    -0.54
     CreateTagHelper
    -0.53
     برانيه
    -0.52
     ketat
    -0.52
     tebal
    -0.51
     leher
    -0.50
     Steep
    -0.50
     poniendo
    -0.50
    POSITIVE LOGITS
     damage
    1.58
     Damage
    1.45
     DAMAGE
    1.43
    damage
    1.36
    Damage
    1.32
     damages
    1.32
     Damages
    1.18
     damaged
    1.18
    DAMAGE
    1.15
     Damaged
    1.13
    Act Density 0.157%

    No Known Activations