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

    Neuronpedia

    INDEX
    Explanations

    shows outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.77
    of
    0.64
    é
    0.62
    ék
    0.61
    ية
    0.60
    are
    0.59
     in
    0.57
     andere
    0.56
    ik
    0.56
     è
    0.56
    POSITIVE LOGITS
    드가
    0.45
     choppy
    0.45
     grumpy
    0.43
    <0x0D>
    0.42
     Bourbon
    0.41
     glycolysis
    0.41
     panther
    0.41
     चोप
    0.40
     indignation
    0.39
     spiders
    0.39
    Act Density 0.956%

    No Known Activations