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

    Neuronpedia

    INDEX
    Explanations

    concepts and terms related to harm and damage, particularly in legal or medical contexts

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

    Harm or damage

    np_acts-logits-general · gemini-2.0-flash

    damage or harm caused

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stateProvider
    -0.59
     snippetHide
    -0.57
    améli
    -0.56
    yntaxException
    -0.54
    UnusedPrivate
    -0.53
    ngdoc
    -0.52
    YLON
    -0.52
    ições
    -0.51
    InputTagHelper
    -0.50
     tartalomajánló
    -0.46
    POSITIVE LOGITS
     inflicted
    1.30
     suffered
    1.23
     done
    1.08
     sustained
    1.02
     incurred
    0.97
     caused
    0.89
    done
    0.87
     Done
    0.81
     endured
    0.81
     inflict
    0.78
    Act Density 0.259%

    No Known Activations