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

    Neuronpedia

    INDEX
    Explanations

    fraud detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mismas
    0.60
     illetve
    0.58
    なども
    0.56
     혹은
    0.56
     등을
    0.55
     Ibid
    0.54
     एवं
    0.54
    Ori
    0.54
    <unused344>
    0.54
     மட்டு
    0.53
    POSITIVE LOGITS
     внима
    0.66
     proble
    0.59
    赶紧
    0.53
     Breeze
    0.53
     plötzlich
    0.52
     blackjack
    0.52
     неправи
    0.52
     girlfriend
    0.51
     правильно
    0.51
     rearranged
    0.51
    Act Density 0.062%

    No Known Activations