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

    Neuronpedia

    INDEX
    Explanations

    reasons and prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Halk
    -0.08
    Danger
    -0.07
     Determ
    -0.07
    Det
    -0.07
    ェ
    -0.07
    كية
    -0.07
    %c
    -0.07
    Gu
    -0.07
     Det
    -0.07
     satisfactory
    -0.07
    POSITIVE LOGITS
     കൊണ്ട
    0.09
     einzig
    0.09
     przede
    0.08
     sucht
    0.08
     ursprünglich
    0.08
     amacı
    0.08
     intending
    0.08
     jeste
    0.08
     kriter
    0.08
     obič
    0.08
    Act Density 0.081%

    No Known Activations