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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SDL
    -0.07
     Cannes
    -0.06
    layan
    -0.06
     times
    -0.06
     buộc
    -0.06
     Và
    -0.06
     Leslie
    -0.06
     кад
    -0.06
     extremely
    -0.06
    ukes
    -0.06
    POSITIVE LOGITS
     �
    0.07
    Closure
    0.07
    �
    0.06
     ACCESS
    0.06
     र
    0.06
    通
    0.06
     unsere
    0.06
    ){//
    0.06
    .sp
    0.06
    (lock
    0.06
    Act Density 0.019%

    No Known Activations