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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and conditions involving variables and parameters

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

    final/last words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.67
     kasarigan
    -0.56
    ThroughAttribute
    -0.56
    MLLoader
    -0.54
    msgTypes
    -0.52
     Autorizaciones
    -0.51
    XmlAccessType
    -0.50
    ScopeManager
    -0.50
     defaultstate
    -0.50
    NameInMap
    -0.49
    POSITIVE LOGITS
     långt
    0.45
     actualidad
    0.45
    GEBURTSDATUM
    0.43
     cuối
    0.43
     annonces
    0.42
     Akhir
    0.40
     dernières
    0.40
     erfaren
    0.40
    最后
    0.39
    finally
    0.39
    Act Density 0.108%

    No Known Activations