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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Türkiye
    -0.09
     manusia
    -0.08
     Türki
    -0.08
     брауз
    -0.08
     cevap
    -0.07
    lob
    -0.07
     Finnish
    -0.07
     içinde
    -0.07
     pendek
    -0.07
    ellä
    -0.07
    POSITIVE LOGITS
     �
    0.08
     spat
    0.08
     Telecom
    0.08
     Comunic
    0.08
     നിന്ന്
    0.08
     നിന്നും
    0.08
    מש
    0.08
     Dept
    0.07
     region
    0.07
     dup
    0.07
    Act Density 0.513%

    No Known Activations