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

    Neuronpedia

    INDEX
    Explanations

    to and colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mell
    -0.07
    メ
    -0.07
     miał
    -0.07
    Newsletter
    -0.07
    栉
    -0.07
    rottle
    -0.06
     Jacob
    -0.06
     Matt
    -0.06
     Hos
    -0.06
    饲养
    -0.06
    POSITIVE LOGITS
     למעלה
    0.07
     guarantees
    0.07
    clarations
    0.06
    cedures
    0.06
    expression
    0.06
    ун
    0.06
     [=
    0.06
     -:
    0.06
    חקירה
    0.06
    开盘
    0.06
    Act Density 0.007%

    No Known Activations