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

    Neuronpedia

    INDEX
    Explanations

    relating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verse
    -0.08
    263
    -0.07
     where
    -0.07
     redund
    -0.07
     moves
    -0.06
     یافته
    -0.06
     TBD
    -0.06
     supports
    -0.06
    ade
    -0.06
     immune
    -0.06
    POSITIVE LOGITS
     relating
    0.28
     thải
    0.07
     deriving
    0.07
    сом
    0.07
     pudding
    0.06
     فوتبال
    0.06
     alcuni
    0.06
     Accountability
    0.06
    işleri
    0.06
     pertaining
    0.06
    Act Density 0.002%

    No Known Activations