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

    Neuronpedia

    INDEX
    Explanations

    bijection, transformations, invertible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ♉
    0.44
     consoles
    0.41
     BSData
    0.40
    Signals
    0.40
     масси
    0.39
    肆章
    0.39
     মাসুদ
    0.39
    👛
    0.39
     calcS
    0.38
    lytres
    0.38
    POSITIVE LOGITS
     bijection
    1.02
     bijective
    1.02
     injective
    0.95
     transformation
    0.91
     bij
    0.91
     transformations
    0.91
     Bij
    0.86
    Bij
    0.83
     Transformation
    0.81
     isomorphisms
    0.80
    Act Density 0.024%

    No Known Activations