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

    Neuronpedia

    INDEX
    Explanations

    cloves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .define
    -0.07
     needless
    -0.07
    ICENSE
    -0.07
    _LANGUAGE
    -0.07
     tangled
    -0.07
    صراع
    -0.07
    מטוס
    -0.07
    发展方向
    -0.07
     punishments
    -0.06
    脫
    -0.06
    POSITIVE LOGITS
    requests
    0.07
     Mavericks
    0.07
    糁
    0.06
     mathematical
    0.06
    (filtered
    0.06
     Graves
    0.06
     explores
    0.06
     cron
    0.06
     ward
    0.06
    legalArgumentException
    0.06
    Act Density 0.002%

    No Known Activations