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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     backpacking
    0.47
     haircuts
    0.46
     transforms
    0.45
     game
    0.44
     matrix
    0.44
     transformed
    0.43
     anime
    0.43
     quarterly
    0.43
     cholesterol
    0.43
     MATRIX
    0.43
    POSITIVE LOGITS
    után
    0.46
    ondon
    0.46
    cias
    0.44
    acios
    0.44
    ffici
    0.44
    Alto
    0.42
    الة
    0.41
    ="")
    0.41
    adinya
    0.41
    Energie
    0.41
    Act Density 0.001%

    No Known Activations