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

    Neuronpedia

    INDEX
    Explanations

    news/analysis excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pai
    -0.07
    reff
    -0.07
     MIT
    -0.07
     accommodating
    -0.07
    ovsky
    -0.06
    κυ
    -0.06
    ～～
    -0.06
     knih
    -0.06
     работ
    -0.06
    álo
    -0.06
    POSITIVE LOGITS
    เท
    0.07
    QUENCY
    0.06
    depth
    0.06
    .getObject
    0.06
     bağlantılar
    0.06
    :E
    0.06
    |^
    0.06
    Secretary
    0.06
     Ak
    0.06
     Sommer
    0.06
    Act Density 0.219%

    No Known Activations