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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ax
    -0.07
     flashback
    -0.06
    encoder
    -0.06
     paragraphs
    -0.06
     Ni
    -0.06
     ais
    -0.06
     مشک
    -0.06
     feather
    -0.06
     şekl
    -0.06
    SUP
    -0.06
    POSITIVE LOGITS
     ‪
    0.06
    <Car
    0.06
    '],↵↵
    0.06
     vows
    0.06
    _CMD
    0.06
     wollte
    0.06
    ()):↵
    0.06
    ツ
    0.06
    docker
    0.06
    贝
    0.06
    Act Density 0.001%

    No Known Activations