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

    Neuronpedia

    INDEX
    Explanations

    content

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cont
    1.52
     cont
    1.47
     kont
    1.43
    Cont
    1.42
     Cont
    1.39
     CONT
    1.30
     Kont
    1.30
    kont
    1.29
    CONT
    1.27
    Kont
    1.20
    POSITIVE LOGITS
     contenus
    1.01
     contenu
    0.99
     содержи
    0.98
     contenuto
    0.96
     contenidos
    0.96
     contents
    0.92
    contents
    0.90
     inhoud
    0.89
     contenido
    0.86
     zaw
    0.86
    Act Density 0.001%

    No Known Activations