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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     animation
    -0.08
     کاری
    -0.07
     �
    -0.06
     doubled
    -0.06
     treaty
    -0.06
    (userID
    -0.06
    раниц
    -0.06
     cửa
    -0.06
     bases
    -0.06
     subsidiary
    -0.06
    POSITIVE LOGITS
    .rel
    0.07
     instructed
    0.07
    лерг
    0.06
    /ws
    0.06
    addComponent
    0.06
     leuk
    0.06
     ann
    0.06
     tabel
    0.06
    /octet
    0.06
    傷
    0.06
    Act Density 0.027%

    No Known Activations