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

    Neuronpedia

    INDEX
    Explanations

    safety and health-related terms and concepts

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

    preceding "of" related to security

    np_acts-logits-general · gemini-2.0-flash

    safety, privacy, welfare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lgari
    -0.59
    NegativeButton
    -0.55
     child
    -0.53
    PathVariable
    -0.52
    物
    -0.51
    migrationBuilder
    -0.51
    ImageField
    -0.49
     فريبيس
    -0.49
    ╚
    -0.48
    AMILY
    -0.47
    POSITIVE LOGITS
     improvement
    0.73
     issues
    0.71
     enhancement
    0.68
     Reſ
    0.67
     assurance
    0.66
     生命周期
    0.66
     improvements
    0.64
     considerations
    0.63
     Normdatei
    0.63
     Houſe
    0.63
    Act Density 0.769%

    No Known Activations