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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons or distinctions among various groups or categories

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

    comparison of groups or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bär
    -0.35
     waard
    -0.34
    väg
    -0.33
     læng
    -0.33
    нгредіє
    -0.32
    お値段
    -0.32
     voeten
    -0.32
     zelve
    -0.32
     věci
    -0.32
     bevis
    -0.31
    POSITIVE LOGITS
     disambiguazione
    0.72
    __(/*!
    0.70
    RegistryLite
    0.61
    хьтан
    0.61
    __":
    0.61
    fjspx
    0.60
    BeginContext
    0.57
    *)((
    0.56
    !*\
    0.56
    outWeight
    0.56
    Act Density 0.196%

    No Known Activations