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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    知识
    -0.07
    фік
    -0.07
    Matchers
    -0.06
     pets
    -0.06
     ecs
    -0.06
     −
    -0.06
     citing
    -0.06
    .from
    -0.06
     dragons
    -0.06
     ubiqu
    -0.06
    POSITIVE LOGITS
     Aberdeen
    0.07
    (inputStream
    0.06
     getters
    0.06
    ger
    0.06
    공지
    0.06
     eski
    0.06
     rfl
    0.06
     Eğer
    0.06
    ughty
    0.06
    plural
    0.06
    Act Density 0.029%

    No Known Activations