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

    Neuronpedia

    INDEX
    Explanations

    discussions related to health, safety, and regulatory compliance

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

    public health and societal issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VYMaps
    -0.49
     lähe
    -0.37
     popcorn
    -0.37
     trink
    -0.36
     sonhos
    -0.35
    queiro
    -0.35
     rêves
    -0.35
    เผ
    -0.35
     CURLOPT
    -0.35
    ähteet
    -0.35
    POSITIVE LOGITS
     promoting
    0.56
     public
    0.55
     protection
    0.55
     prevention
    0.55
    دانشنامهٔ
    0.54
     topics
    0.53
     national
    0.53
     safeguarding
    0.52
     promotion
    0.52
     issues
    0.52
    Act Density 0.016%

    No Known Activations