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

    Neuronpedia

    INDEX
    Explanations

    mentions of guns or violence

    oai_token-act-pair · gemini-2.0-flash

    the word 'gun' and its variations

    np_token-act-pair-logits · gpt-4o-mini

    gun

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.71
    MigrationBuilder
    -0.63
    หวัด
    -0.59
    ComponentModel
    -0.59
     cận
    -0.58
    Bakgrunnsstoff
    -0.56
    mapStateToProps
    -0.55
    HtmlAttribute
    -0.55
     بيها
    -0.54
    édrale
    -0.54
    POSITIVE LOGITS
    depan
    0.49
     Jusqu
    0.44
    jspx
    0.43
     aang
    0.43
     Neat
    0.41
     løs
    0.41
    vedad
    0.40
     tuck
    0.40
     Nether
    0.40
    خلا
    0.40
    Act Density 1.177%

    No Known Activations