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

    Neuronpedia

    INDEX
    Explanations

    terms related to accidents and damage

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

    preceding or relating to "damage"

    np_acts-logits-general · gemini-2.0-flash

    causing damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verture
    -0.53
    __':
    -0.53
    KommentareTeilen
    -0.47
     Fußballspieler
    -0.47
    worten
    -0.44
     fehl
    -0.43
    yntaxException
    -0.43
     APPELLATE
    -0.42
    Statics
    -0.40
    isco
    -0.40
    POSITIVE LOGITS
     damage
    2.62
    damage
    2.26
     Damage
    2.23
     DAMAGE
    2.13
    Damage
    2.09
     damages
    1.96
     harm
    1.96
    DAMAGE
    1.80
     daño
    1.68
     injury
    1.68
    Act Density 0.476%

    No Known Activations