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

    Neuronpedia

    INDEX
    Explanations

    not fully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disproportion
    0.50
     cross
    0.46
    スの
    0.45
     generations
    0.43
     disparity
    0.43
     dependence
    0.43
     проф
    0.42
     Cross
    0.42
     የ
    0.41
     дис
    0.41
    POSITIVE LOGITS
     menuju
    0.61
     tetapi
    0.52
    ه
    0.52
    ្ខ
    0.51
    ר
    0.50
    ai
    0.50
    Nm
    0.49
    गानिस्तान
    0.48
    organiz
    0.48
     estará
    0.47
    Act Density 0.001%

    No Known Activations