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

    Neuronpedia

    INDEX
    Explanations

    concerns related to safety and health risks for individuals and groups

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

    safety and health of passengers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leão
    -0.34
     amine
    -0.34
     essay
    -0.34
     brag
    -0.33
    ﷺ
    -0.32
     defaultdict
    -0.32
     query
    -0.32
    たたみ
    -0.32
    readFileSync
    -0.31
     uVar
    -0.31
    POSITIVE LOGITS
    AddTagHelper
    0.76
    Personensuche
    0.61
    DockStyle
    0.60
    safety
    0.56
     safety
    0.55
     beginnetje
    0.54
    ंदीखरीदारी
    0.53
     Roskov
    0.53
    Safety
    0.51
    inander
    0.51
    Act Density 0.014%

    No Known Activations