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

    Neuronpedia

    INDEX
    Explanations

    Catching Fire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     등
    -0.07
     сделать
    -0.06
     dostate
    -0.06
    三年
    -0.06
    Quit
    -0.06
    овой
    -0.06
    scaled
    -0.06
    �
    -0.06
     limit
    -0.06
    ляли
    -0.06
    POSITIVE LOGITS
     ();↵
    0.07
     :|:
    0.07
     (){↵
    0.07
    _,
    0.06
     heir
    0.06
    (Thread
    0.06
     ipAddress
    0.06
     　　　　　　　　
    0.06
    腐
    0.06
     correction
    0.06
    Act Density 0.000%

    No Known Activations