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

    Neuronpedia

    INDEX
    Explanations

    years of studying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    го
    1.28
    aya
    1.28
     takers
    1.18
     изделий
    1.16
    𝚘
    1.15
    ны
    1.14
    োপাধ্যায়
    1.12
    не
    1.09
    ни
    1.08
     lanzar
    1.07
    POSITIVE LOGITS
     TCA
    1.09
    EDIA
    1.07
    ي
    1.02
    不過
    0.99
    TISE
    0.99
    Dave
    0.97
    s
    0.94
    Collaboration
    0.94
     SEARCH
    0.92
    Suggestion
    0.92
    Act Density 0.048%

    No Known Activations