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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements with units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wavefunction
    0.25
    లేని
    0.23
    麼
    0.22
     trivial
    0.22
    镟
    0.22
     सारे
    0.22
     hadron
    0.22
     soliton
    0.21
     evanescent
    0.21
    :=\
    0.21
    POSITIVE LOGITS
    ish
    0.50
     ish
    0.41
    °
    0.33
    approx
    0.32
    +,
    0.31
    lbs
    0.31
    %)
    0.31
    +.
    0.30
     lbs
    0.30
    %.
    0.29
    Act Density 0.238%

    No Known Activations