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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ch
    -0.07
     سیاست
    -0.07
    eno
    -0.06
     Vie
    -0.06
    적
    -0.06
     Policy
    -0.06
    لام
    -0.06
    _fp
    -0.06
    blr
    -0.06
    -person
    -0.06
    POSITIVE LOGITS
     لغ
    0.07
    <Date
    0.07
    ￣￣￣￣
    0.07
     INTERRUPTION
    0.07
     """
↵
↵
    0.06
     fds
    0.06
    <IM
    0.06
     Longer
    0.06
     жовт
    0.06
     běž
    0.06
    Act Density 0.585%

    No Known Activations