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

    Neuronpedia

    INDEX
    Explanations

    new starting points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     considerable
    0.80
     terdapat
    0.76
     имеется
    0.75
     значительно
    0.70
     obtaining
    0.69
     obtains
    0.68
     имеются
    0.68
     outcrops
    0.68
     remarkable
    0.66
     considerably
    0.66
    POSITIVE LOGITS
    Let
    0.89
    Should
    0.83
     Let
    0.80
     Should
    0.78
    و
    0.73
    Start
    0.71
    ق
    0.70
    Try
    0.70
    我要
    0.69
    Please
    0.69
    Act Density 0.034%

    No Known Activations