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

    Neuronpedia

    INDEX
    Explanations

    structured lists and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    веде
    0.54
     calculating
    0.51
    मेद
    0.51
     whitish
    0.50
     sumptuous
    0.50
     મોત
    0.50
     heady
    0.49
    댕
    0.49
     primera
    0.49
     appending
    0.48
    POSITIVE LOGITS
    '
    0.61
    <0x0D>
    0.60
     (
    0.59
    Many
    0.55
    ,
    0.53
    :
    0.51
    ’
    0.51
    ş
    0.51
    But
    0.51
    -
    0.50
    Act Density 0.199%

    No Known Activations