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

    Neuronpedia

    INDEX
    Explanations

    segments that indicate actions or directives

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

    links and book references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     citer
    -0.31
    ::::::::
    -0.31
     مشين
    -0.30
    ртка
    -0.29
    folg
    -0.28
    userdetails
    -0.28
     پای
    -0.27
    fycat
    -0.27
    fieldLabel
    -0.27
     the
    -0.26
    POSITIVE LOGITS
     فريبيس
    0.77
     nonUne
    0.75
    tagHelperRunner
    0.75
     
    0.73
     ""],
    0.72
    :✨
    0.69
    Aiheesta
    0.69
    httphttps
    0.68
    Diwedd
    0.64
     <",
    0.61
    Act Density 0.006%

    No Known Activations