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

    Neuronpedia

    INDEX
    Explanations

    units of length and measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     арен
    0.66
     Rooms
    0.65
     시
    0.61
     binary
    0.61
    批判
    0.60
    authState
    0.60
    묽
    0.60
     habilit
    0.59
     бібліоте
    0.59
    衮
    0.59
    POSITIVE LOGITS
     inches
    1.89
     Inches
    1.65
    cm
    1.64
    inches
    1.62
     cm
    1.58
     centimeters
    1.55
     centimetres
    1.53
    inch
    1.48
     centimeter
    1.45
     inch
    1.45
    Act Density 0.107%

    No Known Activations