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

    Neuronpedia

    INDEX
    Explanations

    transform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     played
    -0.07
     icy
    -0.06
     rallies
    -0.06
     listens
    -0.06
    _entries
    -0.06
    唱
    -0.06
    -history
    -0.06
     runs
    -0.06
     plays
    -0.06
    領
    -0.06
    POSITIVE LOGITS
     transformation
    0.11
     Transformation
    0.10
     transforming
    0.10
     transform
    0.09
     transformed
    0.08
     Transform
    0.07
    birthday
    0.07
    株式会社
    0.07
     мас
    0.06
    	transform
    0.06
    Act Density 0.013%

    No Known Activations