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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ASP
    -0.08
     gram
    -0.07
    SPA
    -0.07
    ્પ
    -0.07
     ƙ
    -0.07
     attribution
    -0.07
    AR
    -0.07
     Tim
    -0.07
     jeux
    -0.07
    ‍්
    -0.07
    POSITIVE LOGITS
     приблиз
    0.09
    otive
    0.09
     przygot
    0.08
     Lieutenant
    0.08
     отвеч
    0.08
     bó
    0.08
     monot
    0.08
     chaleure
    0.07
     obnox
    0.07
    Herr
    0.07
    Act Density 0.001%

    No Known Activations