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

    Neuronpedia

    INDEX
    Explanations

    football match scores and draws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আগ্রহী
    0.34
     krótk
    0.32
     alimento
    0.32
     ஆய்வு
    0.31
     Found
    0.30
     फाउंड
    0.30
     आढळ
    0.30
     باید
    0.29
     takich
    0.29
     bilir
    0.29
    POSITIVE LOGITS
     despite
    0.35
    을
    0.35
    。
    0.34
    sending
    0.32
     with
    0.31
    ！
    0.30
    后的
    0.29
    despite
    0.29
    ﻴ
    0.29
     στην
    0.29
    Act Density 0.009%

    No Known Activations