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

    Neuronpedia

    INDEX
    Explanations

    Punctuation, varied sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     любов
    -0.07
     declines
    -0.06
     SIM
    -0.06
     Frequently
    -0.06
    _dispatch
    -0.06
     dips
    -0.06
     factions
    -0.06
     minlength
    -0.06
     returns
    -0.06
     primitive
    -0.06
    POSITIVE LOGITS
     кни
    0.07
    leston
    0.07
    Paragraph
    0.06
     travelling
    0.06
     пох
    0.06
    ichage
    0.06
    τική
    0.06
     somew
    0.06
     پل
    0.06
    lew
    0.06
    Act Density 0.000%

    No Known Activations