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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kot
    -0.07
    scores
    -0.07
    бут
    -0.06
     MASK
    -0.06
     chiếu
    -0.06
    �
    -0.06
    .ar
    -0.06
    طن
    -0.06
     กรกฎ
    -0.06
     따
    -0.06
    POSITIVE LOGITS
     cookbook
    0.07
    увати
    0.06
     наук
    0.06
    Une
    0.06
    580
    0.06
    สถานท
    0.06
     LoginPage
    0.06
     greatly
    0.06
    )}"↵
    0.06
    (User
    0.06
    Act Density 0.000%

    No Known Activations