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

    Neuronpedia

    INDEX
    Explanations

    certainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    encoding
    -0.07
    }">↵
    -0.06
     잡담
    -0.06
     ion
    -0.06
    odb
    -0.06
     SF
    -0.06
    ?('
    -0.06
    -player
    -0.06
    英語
    -0.06
     Hermione
    -0.06
    POSITIVE LOGITS
    Sketch
    0.06
     Dul
    0.06
    Ian
    0.06
    boards
    0.06
     contempor
    0.06
     mund
    0.06
     reckless
    0.06
     ocean
    0.06
    Tu
    0.06
     rob
    0.06
    Act Density 0.178%

    No Known Activations