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

    Neuronpedia

    INDEX
    Explanations

    Recommendations and varied limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ное
    0.49
    akk
    0.49
     Fantasy
    0.47
    サ
    0.46
     도
    0.45
     kip
    0.44
     móviles
    0.44
    ная
    0.43
     신
    0.43
    개발
    0.42
    POSITIVE LOGITS
     poured
    0.55
    f
    0.48
    )।
    0.47
    );
    0.46
    etrically
    0.46
     commissioned
    0.46
    utig
    0.46
     questa
    0.44
    Questa
    0.44
    ).
    0.44
    Act Density 0.000%

    No Known Activations