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

    Neuronpedia

    INDEX
    Explanations

    food products and technology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    -2.64
    s
    -2.44
    U
    -2.28
    ’
    -2.13
     
    -2.08
    WAUKEE
    -2.06
    非常に
    -2.05
                    
    -1.99
     siendo
    -1.95
    清醒
    -1.95
    POSITIVE LOGITS
    .
    2.89
    ⬜
    2.30
     juſ
    2.25
     แต่
    2.17
     is
    2.14
    GillaGilla
    2.09
     Gutes
    2.08
     theses
    2.05
    schule
    2.03
    墻
    2.03
    Act Density 0.020%

    No Known Activations