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

    Neuronpedia

    INDEX
    Explanations

    variables and data structures in code

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

    indexed variables and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lanjut
    -0.39
    NamedQueries
    -0.34
     award
    -0.33
    Superview
    -0.33
     accomplished
    -0.28
    ไ
    -0.28
    responseData
    -0.28
    .
    -0.28
    runOn
    -0.28
     du
    -0.27
    POSITIVE LOGITS
     دیکھیے
    0.76
    ſelf
    0.70
     الحره
    0.65
    CloseOperation
    0.63
     ComVisible
    0.62
     dieſen
    0.61
    الحياه
    0.60
    SequentialGroup
    0.60
     témoig
    0.60
     ſind
    0.59
    Act Density 0.009%

    No Known Activations