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

    Neuronpedia

    INDEX
    Explanations

    paper sizes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Cascade
    -0.06
     Goods
    -0.06
    омер
    -0.06
    *[
    -0.06
    аря
    -0.06
    (send
    -0.06
    elez
    -0.06
    _statistics
    -0.06
    -acre
    -0.06
    441
    -0.06
    POSITIVE LOGITS
    Leg
    0.07
     fos
    0.07
     getToken
    0.07
     interacts
    0.06
     Amb
    0.06
     lawful
    0.06
     gerektiğini
    0.06
     інформа
    0.06
    /log
    0.06
    において
    0.06
    Act Density 0.023%

    No Known Activations