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

    Neuronpedia

    INDEX
    Explanations

    grammatical cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     determined
    0.39
    Character
    0.37
    Complex
    0.37
    ያ
    0.37
    Pan
    0.36
     understood
    0.36
    latin
    0.36
     tried
    0.36
    PERSONAL
    0.35
    An
    0.35
    POSITIVE LOGITS
     Franken
    0.43
     ફે
    0.38
    EndZ
    0.38
     Frankfurter
    0.37
    굼
    0.37
     cytometry
    0.37
     Franks
    0.36
    度的
    0.36
     FRG
    0.36
     FX
    0.36
    Act Density 0.000%

    No Known Activations