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

    Neuronpedia

    INDEX
    Explanations

    null hypothesis testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     солне
    0.66
     後
    0.63
     unrival
    0.61
     масла
    0.59
    erb
    0.59
     আশ্বাস
    0.59
     YT
    0.58
     offrire
    0.57
     марки
    0.57
    䛛
    0.57
    POSITIVE LOGITS
    ath
    0.77
    ın
    0.71
    as
    0.69
    ak
    0.67
     hypothesis
    0.63
    1
    0.63
    아
    0.63
    əd
    0.61
    ă
    0.60
    loaded
    0.59
    Act Density 0.014%

    No Known Activations