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

    Neuronpedia

    INDEX
    Explanations

    how and why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nek
    0.57
     जानना
    0.54
     książ
    0.50
     Perkenalkan
    0.50
     literatura
    0.49
     জানেন
    0.49
    orice
    0.49
     unmistak
    0.49
     දක්
    0.49
     törté
    0.48
    POSITIVE LOGITS
    ان
    0.63
    ی
    0.59
    an
    0.54
     why
    0.51
    ब्र
    0.50
    ినా
    0.48
    یوں
    0.47
     Why
    0.47
     aten
    0.47
    Pourquoi
    0.47
    Act Density 0.011%

    No Known Activations