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

    Neuronpedia

    INDEX
    Explanations

    (-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ساز
    -0.07
    �
    -0.07
     하지
    -0.06
     coast
    -0.06
    阳
    -0.06
     Scala
    -0.06
    KindOfClass
    -0.06
     Wang
    -0.06
    690
    -0.06
     Gund
    -0.06
    POSITIVE LOGITS
    Ep
    0.07
    __)↵
    0.07
     Seks
    0.06
    AWN
    0.06
     ){↵↵
    0.06
     Raven
    0.06
    MENU
    0.06
    _REFERER
    0.06
     desar
    0.06
     credential
    0.06
    Act Density 0.006%

    No Known Activations