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

    Neuronpedia

    INDEX
    Explanations

    chat logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    todos
    -0.07
     portfolio
    -0.07
     ransom
    -0.06
     organ
    -0.06
    utar
    -0.06
    ーティ
    -0.06
     Imam
    -0.06
     debate
    -0.06
    .BL
    -0.06
     را
    -0.06
    POSITIVE LOGITS
     sealing
    0.06
    (md
    0.06
     까
    0.06
     DISCLAIMED
    0.06
     Imported
    0.06
     엔
    0.06
     "-";↵
    0.06
     ورود
    0.06
     vielleicht
    0.06
     vacancies
    0.06
    Act Density 0.032%

    No Known Activations