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

    Neuronpedia

    INDEX
    Explanations

    decom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ❵
    -0.07
     ance
    -0.07
    Adv
    -0.06
     soap
    -0.06
    ,end
    -0.06
     speaking
    -0.06
    employer
    -0.06
     **)&
    -0.06
     fool
    -0.06
     Howe
    -0.06
    POSITIVE LOGITS
    恝
    0.07
    毌
    0.07
    军
    0.07
    =".$
    0.07
     điều
    0.07
    [ii
    0.07
    forcements
    0.07
     Sağlık
    0.07
     mojo
    0.07
    챠
    0.07
    Act Density 0.004%

    No Known Activations