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

    Neuronpedia

    INDEX
    Explanations

    propagation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Мед
    -0.07
    -region
    -0.07
    TE
    -0.07
     Irene
    -0.07
    З
    -0.07
     ties
    -0.06
     zvol
    -0.06
    ñas
    -0.06
     routine
    -0.06
     Osw
    -0.06
    POSITIVE LOGITS
     proposition
    0.07
    PlainOldData
    0.07
     ]];
    0.07
     launched
    0.07
    .")]↵
    0.06
    (undefined
    0.06
     Swagger
    0.06
     ژاپ
    0.06
    파트
    0.06
     propag
    0.06
    Act Density 0.002%

    No Known Activations