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

    Neuronpedia

    INDEX
    Explanations

    content related to safety ratings and features in vehicles

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

    safety characteristics and concerns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.46
    istoitu
    -0.41
     OFDb
    -0.40
    UnusedPrivate
    -0.39
     StringTokenizer
    -0.39
    MethodManager
    -0.38
     Италијани
    -0.38
    tagHelperRunner
    -0.38
    addPreferredGap
    -0.38
     onCreateView
    -0.37
    POSITIVE LOGITS
     safety
    0.68
     Safety
    0.59
    Safety
    0.57
    safety
    0.54
     SAFETY
    0.49
     safer
    0.48
    Volvo
    0.47
    安全
    0.47
     acci
    0.45
    SAFETY
    0.45
    Act Density 0.008%

    No Known Activations