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

    Neuronpedia

    INDEX
    Explanations

    asking for more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clar
    0.47
     clar
    0.46
    certain
    0.46
     elaborated
    0.45
     elabor
    0.44
     further
    0.44
     elaborate
    0.42
     Elabor
    0.42
    enna
    0.41
     Further
    0.41
    POSITIVE LOGITS
     ones
    0.47
    Attempt
    0.44
     такими
    0.44
     આવા
    0.44
     dozens
    0.44
     подобные
    0.43
    ুদ্ধে
    0.41
    类似的
    0.41
     suje
    0.40
     ശ്രമ
    0.40
    Act Density 0.038%

    No Known Activations