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

    Neuronpedia

    INDEX
    Explanations

    subscripts and exponents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     metastable
    0.64
     precipitate
    0.63
     metamorphic
    0.63
     homeostasis
    0.63
     finite
    0.62
     sedimentary
    0.62
     divalent
    0.60
     abelian
    0.59
     finitely
    0.59
     codimension
    0.59
    POSITIVE LOGITS
    Hlav
    0.64
    Pull
    0.64
    Buenos
    0.57
    itto
    0.56
     Pull
    0.55
    Brend
    0.54
     Sponsorship
    0.54
    RT
    0.54
    Craft
    0.54
    Checkout
    0.54
    Act Density 0.000%

    No Known Activations