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

    Neuronpedia

    INDEX
    Explanations

    lemma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Impression
    -0.09
     Commissioners
    -0.08
     shuffled
    -0.08
     印
    -0.08
     collage
    -0.08
     exemplar
    -0.08
     Portland
    -0.08
     Hann
    -0.07
    .shuffle
    -0.07
    processors
    -0.07
    POSITIVE LOGITS
     lemma
    0.12
    Lemma
    0.10
     gcd
    0.10
    _formula
    0.09
     Lem
    0.09
     fiery
    0.08
     formula
    0.08
     lem
    0.08
     contests
    0.08
     ಗಾಯ
    0.08
    Act Density 0.001%

    No Known Activations