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

    Neuronpedia

    INDEX
    Explanations

    chatbot assistant text generation

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     машин
    -0.08
    طرف
    -0.07
     поиск
    -0.07
    info
    -0.07
    Tw
    -0.07
    꼽
    -0.07
     Именно
    -0.07
     назад
    -0.07
    limited
    -0.06
    thesize
    -0.06
    POSITIVE LOGITS
    ConstraintMaker
    0.08
    pieczeń
    0.07
    .moveToFirst
    0.07
    퀄
    0.07
     joked
    0.07
     Crom
    0.07
    潺
    0.07
    哭泣
    0.07
     להגיד
    0.07
    компон
    0.07
    Act Density 0.017%

    No Known Activations