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

    Neuronpedia

    INDEX
    Explanations

    parts and components

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Super
    0.86
    Super
    0.73
     C
    0.55
     Class
    0.50
     الص
    0.48
     Супер
    0.47
     Sub
    0.46
     Out
    0.45
    Out
    0.45
    Class
    0.43
    POSITIVE LOGITS
     Tem
    0.42
     Се
    0.40
     Ce
    0.39
     Nev
    0.39
    Tem
    0.39
     Common
    0.39
     Ста
    0.39
     Seguridad
    0.39
    Пред
    0.39
    Geme
    0.38
    Act Density 0.015%

    No Known Activations