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

    Neuronpedia

    INDEX
    Explanations

    percentages and statistical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    percentages and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Décès
    -0.40
    短短
    -0.39
     således
    -0.38
    savevideo
    -0.37
    Cuántos
    -0.36
    قایناقلار
    -0.35
     nhiều
    -0.35
    many
    -0.35
     unterkunft
    -0.34
    writeFieldEnd
    -0.34
    POSITIVE LOGITS
    ValueStyle
    0.67
     probably
    0.66
     Probably
    0.62
    probably
    0.59
    المشاركات
    0.57
     maybe
    0.56
    Probably
    0.56
     pinulongan
    0.54
     ivelany
    0.52
    AddTagHelper
    0.52
    Act Density 0.026%

    No Known Activations