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

    Neuronpedia

    INDEX
    Explanations

    phrases and sentiments reflecting complex emotional states and situations involving external pressures or expectations

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

    all this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     administração
    -0.44
     senhora
    -0.43
     conclusão
    -0.42
     prática
    -0.42
    之
    -0.41
     vítima
    -0.41
     prácticas
    -0.41
     otras
    -0.40
     hänen
    -0.40
     אז
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.60
    complexContent
    0.56
    Rhestr
    0.55
    ValueStyle
    0.55
    PMailer
    0.54
    évaluateur
    0.53
    Cyfarwyddwr
    0.52
    ArrowToggle
    0.52
    VersionUID
    0.52
    انتهای
    0.52
    Act Density 0.033%

    No Known Activations