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

    Neuronpedia

    INDEX
    Explanations

    common elements in a structured dataset, especially related to competitions or challenges

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

    dataset names and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cinturón
    -0.31
    互
    -0.30
    abs
    -0.30
    avení
    -0.30
     conclure
    -0.29
    ียบ
    -0.29
    lies
    -0.28
     thụ
    -0.28
    一条
    -0.28
     trovo
    -0.28
    POSITIVE LOGITS
    EndContext
    0.62
    mystery
    0.61
     Mystery
    0.59
    Mystery
    0.59
    principalTable
    0.58
     NSCoder
    0.57
    الإنجليزية
    0.56
     betweenstory
    0.55
     mystery
    0.54
    MLLoader
    0.50
    Act Density 0.046%

    No Known Activations