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

    Neuronpedia

    INDEX
    Explanations

    ’s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    weeted
    -0.07
    ucked
    -0.06
    落
    -0.06
    しま
    -0.06
    епти
    -0.06
    occasion
    -0.06
    ucks
    -0.06
    的手
    -0.06
    Ò
    -0.06
    POSITIVE LOGITS
     prescribed
    0.07
     converter
    0.06
     Excellent
    0.06
    llum
    0.06
     codecs
    0.06
     Stellar
    0.06
     Equals
    0.06
    active
    0.06
     visitors
    0.06
     champions
    0.06
    Act Density 0.041%

    No Known Activations