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

    Neuronpedia

    INDEX
    Explanations

    Likelihood/probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prone
    -0.09
     anaer
    -0.08
     menj
    -0.08
    Primitive
    -0.08
     Comparing
    -0.08
     эх
    -0.08
     anb
    -0.08
     eut
    -0.07
     remet
    -0.07
    metik
    -0.07
    POSITIVE LOGITS
    事情
    0.08
    plural
    0.08
     julọ
    0.08
    ที่สุด
    0.08
    isatie
    0.07
     ترین
    0.07
     ביותר
    0.07
    stay
    0.07
     Aunque
    0.07
     events
    0.07
    Act Density 0.005%

    No Known Activations