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

    Neuronpedia

    INDEX
    Explanations

    instances of specific mathematical or programming symbols and keywords

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ist
    -0.38
    yszer
    -0.36
    pel
    -0.35
    مئ
    -0.34
    ome
    -0.34
     understandable
    -0.34
    getItemId
    -0.34
     Schol
    -0.33
    od
    -0.33
     posed
    -0.33
    POSITIVE LOGITS
     surla
    0.80
    :✨
    0.75
    Personendaten
    0.72
     kasarigan
    0.71
    帖最后由
    0.64
     الحره
    0.64
     informée
    0.58
     plufieurs
    0.57
     незавершена
    0.56
     ägg
    0.56
    Act Density 0.000%

    No Known Activations