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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mpjes
    -0.07
    ичного
    -0.07
     soutě
    -0.06
    FR
    -0.06
    ิโล
    -0.06
     tích
    -0.06
    <Rigidbody
    -0.06
     réseau
    -0.06
    .dev
    -0.06
    电视
    -0.06
    POSITIVE LOGITS
    _paragraph
    0.08
     ام
    0.07
    Undo
    0.07
     outbreaks
    0.07
     strut
    0.07
    义
    0.07
     taped
    0.07
     Paragraph
    0.07
     gul
    0.06
     Dover
    0.06
    Act Density 0.017%

    No Known Activations