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

    Neuronpedia

    INDEX
    Explanations

    size and length

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আকারে
    0.37
     speeds
    0.36
     力
    0.36
    能不能
    0.36
    urin
    0.35
     Configurations
    0.35
     ropes
    0.34
     Sizes
    0.34
    나요
    0.34
    ାନ
    0.34
    POSITIVE LOGITS
     length
    0.62
     circumference
    0.61
     stature
    0.56
     diameter
    0.55
    length
    0.53
     lenght
    0.51
     duration
    0.49
     lunghezza
    0.48
     длину
    0.47
    circum
    0.47
    Act Density 0.007%

    No Known Activations