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

    Neuronpedia

    INDEX
    Explanations

    foreign language markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شرطونو
    0.44
    ଝ
    0.42
     stockno
    0.42
    Ꮰ
    0.41
    Ᏸ
    0.41
    Ꮁ
    0.41
    ナソニック
    0.40
     พิจิก
    0.40
     الحره
    0.40
    俄
    0.40
    POSITIVE LOGITS
     der
    0.52
     För
    0.50
     automat
    0.49
     Gün
    0.47
     al
    0.47
     por
    0.47
     des
    0.46
     kon
    0.46
     Eks
    0.46
     Über
    0.46
    Act Density 0.000%

    No Known Activations