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

    Neuronpedia

    INDEX
    Explanations

    output sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abhid
    0.52
    側の
    0.52
    ėtų
    0.50
    czych
    0.49
    ující
    0.48
    क्ष्य
    0.48
    ik
    0.47
     బ్లా
    0.47
    痂
    0.47
     পক্ষের
    0.46
    POSITIVE LOGITS
    ocurrencies
    0.53
    lement
    0.51
     nuovi
    0.46
     %
    0.46
    enaire
    0.45
    Are
    0.44
     Are
    0.44
     nuevas
    0.43
    %
    0.42
     %,
    0.42
    Act Density 0.001%

    No Known Activations