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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -English
    -0.08
    apost
    -0.08
     фундамент
    -0.08
     оку
    -0.08
    igst
    -0.08
     provenance
    -0.08
     ಸುಮಾರು
    -0.08
     coeur
    -0.07
    insured
    -0.07
     ayant
    -0.07
    POSITIVE LOGITS
     quirky
    0.09
     comedic
    0.09
    Bubble
    0.09
     goofy
    0.08
     misch
    0.08
    Halloween
    0.08
    快乐
    0.08
     comedy
    0.08
     toddlers
    0.08
     bubble
    0.08
    Act Density 0.030%

    No Known Activations