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

    Neuronpedia

    INDEX
    Explanations

    Code installation instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     morto
    -0.08
     prima
    -0.08
     illusion
    -0.07
     गीत
    -0.07
    Bonus
    -0.07
    odz
    -0.07
     दिव
    -0.07
    )._
    -0.07
     multipl
    -0.07
     sells
    -0.07
    POSITIVE LOGITS
    ഘ
    0.07
     Config
    0.07
     &&
    0.07
     abonn
    0.07
     scoop
    0.07
     Biod
    0.07
     перей
    0.07
     тепло
    0.07
     AND
    0.07
    (www
    0.07
    Act Density 0.003%

    No Known Activations