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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    extracomment
    -0.06
     आय
    -0.06
    Motor
    -0.06
    Translator
    -0.06
    _Master
    -0.06
    잖
    -0.06
    .order
    -0.06
     hurd
    -0.06
     Emma
    -0.06
     Herz
    -0.06
    POSITIVE LOGITS
       ↵
    0.07
    Measured
    0.06
    ặc
    0.06
     persone
    0.06
     boring
    0.06
    �
    0.06
    	files
    0.06
    _Response
    0.06
     форм
    0.06
    ....↵↵
    0.06
    Act Density 0.001%

    No Known Activations