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

    Neuronpedia

    INDEX
    Explanations

    must

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.09
    �
    -0.07
     usleep
    -0.07
     Vaugh
    -0.07
    مسل
    -0.07
     phòng
    -0.06
    倧
    -0.06
    Ignore
    -0.06
    俄乌
    -0.06
    槁
    -0.06
    POSITIVE LOGITS
     LEDs
    0.08
    เสมอ
    0.07
     Messiah
    0.07
    alan
    0.07
    criptor
    0.07
    abilities
    0.07
    ERGY
    0.06
     repreh
    0.06
     rogue
    0.06
     belongings
    0.06
    Act Density 0.029%

    No Known Activations