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

    Neuronpedia

    INDEX
    Explanations

    err

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     día
    -0.07
     genome
    -0.06
     completo
    -0.06
     Ric
    -0.06
     polynomial
    -0.06
     Mama
    -0.06
     USER
    -0.06
     Dios
    -0.06
     Από
    -0.06
    _gray
    -0.06
    POSITIVE LOGITS
    rr
    0.08
     �
    0.07
     CSL
    0.07
    рас
    0.06
     اش
    0.06
    एस
    0.06
    :ss
    0.06
     استرات
    0.06
     permit
    0.06
    ss
    0.06
    Act Density 0.008%

    No Known Activations