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

    Neuronpedia

    INDEX
    Explanations

    phrases that express obligations and permissions within a community or service context

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

    modal verbs and auxiliaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.85
    ⓧ
    -0.65
     Administrativna
    -0.65
     kasarigan
    -0.63
     Geſch
    -0.63
     Infórmanos
    -0.61
    Portail
    -0.60
    MessageTagHelper
    -0.59
    Personendaten
    -0.59
    󠁣
    -0.56
    POSITIVE LOGITS
     means
    0.34
     débar
    0.31
    ViewImports
    0.30
    тельно
    0.29
    Dear
    0.28
    alpha
    0.27
    ed
    0.27
     potentially
    0.27
     minim
    0.27
     consequently
    0.27
    Act Density 0.069%

    No Known Activations