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

    Neuronpedia

    INDEX
    Explanations

    absence of what is essential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thereby
    0.47
     should
    0.46
     Thereby
    0.46
     তারপর
    0.45
     kudu
    0.44
     এরপর
    0.43
    ควร
    0.43
    くなった
    0.43
     dadurch
    0.43
    从而
    0.42
    POSITIVE LOGITS
    否则
    0.64
     merely
    0.61
     wouldn
    0.61
     otherwise
    0.59
     olmaz
    0.59
    就不会
    0.57
     Otherwise
    0.55
    otherwise
    0.55
     sonst
    0.54
    Otherwise
    0.54
    Act Density 0.011%

    No Known Activations