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

    Neuronpedia

    INDEX
    Explanations

    verb + preposition/adverb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.26
     and
    0.26
    j
    0.25
     这些
    0.25
     of
    0.25
    ov
    0.24
     oder
    0.24
    ern
    0.23
    etera
    0.23
    lings
    0.23
    POSITIVE LOGITS
     culmin
    0.27
    꽤
    0.26
     horribly
    0.25
     représenter
    0.25
     quite
    0.25
     undeni
    0.25
    Methylsulfanyl
    0.25
     squarely
    0.24
    ۸
    0.24
     nuestra
    0.24
    Act Density 0.472%

    No Known Activations