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

    Neuronpedia

    INDEX
    Explanations

    Code and layout elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тер
    -0.09
     temporal
    -0.08
     chronological
    -0.08
     ಮಾರ
    -0.08
     ped
    -0.08
     metaphor
    -0.08
    olon
    -0.08
    и
    -0.07
     senator
    -0.07
     osi
    -0.07
    POSITIVE LOGITS
     Fen
    0.08
     Kek
    0.08
     ausgeschlossen
    0.07
     restricciones
    0.07
    、自
    0.07
    (calc
    0.07
     rappel
    0.07
     Constraints
    0.07
    Restriction
    0.07
    ren
    0.07
    Act Density 0.003%

    No Known Activations