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

    Neuronpedia

    INDEX
    Explanations

    :?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’da
    -0.07
     increase
    -0.06
    EndPoint
    -0.06
    .Repository
    -0.06
    �
    -0.06
     Me
    -0.06
    istribution
    -0.06
     artillery
    -0.06
     deprivation
    -0.06
    Ending
    -0.06
    POSITIVE LOGITS
     гот
    0.07
    [++
    0.07
    학년도
    0.07
     straně
    0.07
    �
    0.07
     grunt
    0.07
    �
    0.06
     pony
    0.06
    076
    0.06
     поє
    0.06
    Act Density 0.000%

    No Known Activations