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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing difficulty or challenges in understanding or believing something

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

    find it hard/easy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.92
     препратки
    -0.78
     betweenstory
    -0.73
     propOrder
    -0.71
     queſta
    -0.71
    下载附件
    -0.71
     مشين
    -0.71
     виправивши
    -0.67
     للاسماء
    -0.67
    FunctionFlags
    -0.66
    POSITIVE LOGITS
     Find
    0.39
     find
    0.35
    Find
    0.34
     FIND
    0.34
     prominent
    0.33
    wp
    0.32
    find
    0.31
     enjoy
    0.30
    tend
    0.30
    FIND
    0.28
    Act Density 0.011%

    No Known Activations