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

    Neuronpedia

    INDEX
    Explanations

    academic references and code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Till
    0.74
    UNG
    0.66
     vart
    0.63
    トップ
    0.61
    スー
    0.61
    луб
    0.61
    jeeling
    0.60
    Spor
    0.60
    Fac
    0.60
    Bub
    0.59
    POSITIVE LOGITS
    cite
    1.44
     cite
    1.27
     Cite
    1.08
     citing
    1.06
    citep
    1.05
     cit
    1.04
     citations
    1.02
     citation
    1.01
    eqref
    1.01
     cited
    0.97
    Act Density 0.034%

    No Known Activations