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

    Neuronpedia

    INDEX
    Explanations

    the followed by abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.59
    1
    0.54
    8
    0.50
    6
    0.48
    (
    0.48
    :
    0.46
    =
    0.45
    '
    0.44
    4
    0.43
    +
    0.43
    POSITIVE LOGITS
     intricacies
    0.64
     complexities
    0.63
     süreç
    0.53
     allerlei
    0.52
     microcosm
    0.52
     ecosystems
    0.52
     vielfält
    0.51
     environments
    0.50
     nuances
    0.50
     lifecycle
    0.49
    Act Density 0.078%

    No Known Activations