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

    Neuronpedia

    INDEX
    Explanations

    lines of XML or code containing assignment or value assignment statements

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

    XML and HTML attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfieras
    -0.32
     suspensión
    -0.32
     negó
    -0.31
    gridy
    -0.31
    Izvori
    -0.31
    ContentLoaded
    -0.30
    ob
    -0.30
     véri
    -0.28
    PMailer
    -0.28
     mo
    -0.27
    POSITIVE LOGITS
    Personendaten
    0.68
     Италијани
    0.63
     للمعارف
    0.63
     GenerationType
    0.62
    참고
    0.60
    NameInMap
    0.59
    ✭✭
    0.59
     يتيمه
    0.56
     ujednoznacz
    0.54
     FetchType
    0.54
    Act Density 0.007%

    No Known Activations