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

    Neuronpedia

    INDEX
    Explanations

    technical instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carbon
    -0.08
     apples
    -0.07
    .delete
    -0.07
    од
    -0.07
    Car
    -0.07
     carving
    -0.07
    odor
    -0.07
    estor
    -0.07
     shock
    -0.07
    ेरी
    -0.07
    POSITIVE LOGITS
     Regeln
    0.09
     Kalender
    0.09
     darparu
    0.09
     Studenten
    0.09
     definição
    0.09
     Definitions
    0.08
     Calabria
    0.08
     Dusche
    0.08
     aturan
    0.08
     Auswahl
    0.08
    Act Density 0.054%

    No Known Activations