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

    Neuronpedia

    INDEX
    Explanations

    pay it forward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     чер
    0.59
     Бала
    0.56
    es
    0.55
    ]].
    0.53
    ată
    0.52
    chessboard
    0.51
    igay
    0.51
    ataka
    0.50
    ad
    0.50
     дела
    0.49
    POSITIVE LOGITS
     kulture
    0.54
     revolution
    0.52
     deber
    0.51
    ূন্য
    0.50
     deception
    0.47
     sinds
    0.45
    溶
    0.44
     downtime
    0.43
    文化的
    0.43
    我们
    0.43
    Act Density 0.001%

    No Known Activations