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

    Neuronpedia

    INDEX
    Explanations

    references to health-related issues and conditions

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

    Risk reduction or prevention

    np_acts-logits-general · gemini-2.0-flash

    prevention and mitigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.61
    adpleegd
    -0.59
    ItemBackground
    -0.57
    TintMode
    -0.54
    ագրություններ
    -0.54
    ctype
    -0.53
     GlobalKey
    -0.53
     Preferencias
    -0.51
     Unavailable
    -0.51
    ContentAlignment
    -0.50
    POSITIVE LOGITS
     prevention
    1.15
     Prevention
    1.03
    prevention
    0.99
     mitigation
    0.95
    Prevention
    0.92
     elimination
    0.89
     reduction
    0.87
     eliminated
    0.87
    elimin
    0.83
     minimized
    0.82
    Act Density 0.852%

    No Known Activations