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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collects
    -0.07
    decorate
    -0.07
     NIGHT
    -0.06
     MORE
    -0.06
    Nat
    -0.06
     정책
    -0.06
     Many
    -0.06
     transcripts
    -0.06
    nation
    -0.06
     HtmlWebpackPlugin
    -0.06
    POSITIVE LOGITS
    ُه
    0.06
    )/(
    0.06
    )*
    0.06
     *(
    0.06
    скільки
    0.06
    .es
    0.06
    featured
    0.06
    )/
    0.06
    /The
    0.06
    )\↵
    0.06
    Act Density 0.019%

    No Known Activations