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

    Neuronpedia

    INDEX
    Explanations

    include, as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vị
    -0.07
    ()`
    -0.07
     refer
    -0.07
    SIGN
    -0.06
    ERCHANTABILITY
    -0.06
    traditional
    -0.06
     conveyor
    -0.06
     Romanian
    -0.06
     لها
    -0.06
    oooo
    -0.06
    POSITIVE LOGITS
     плит
    0.06
     alleging
    0.06
    MITTED
    0.06
    Installing
    0.06
    .grid
    0.06
     біблі
    0.06
     Scre
    0.06
     Stellar
    0.06
     fabrics
    0.06
    ليف
    0.06
    Act Density 0.027%

    No Known Activations