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

    Neuronpedia

    INDEX
    Explanations

    references to authorship or the presence of individuals in the text

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

    publication year and journal article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.52
    -0.50
    fortawesome
    -0.45
    /**
    -0.45
    تقاوى
    -0.45
     Italijani
    -0.44
    LookAnd
    -0.43
     BoxFit
    -0.42
     Biôgrafia
    -0.42
    ⓧ
    -0.42
    POSITIVE LOGITS
    出版年
    0.69
    期刊论文
    0.68
    
    0.54
     nahilalakip
    0.51
     }}$}
    0.49
    Handlung
    0.46
     
    0.44
    acles
    0.44
    Tikang
    0.44
     ")");
    0.44
    Act Density 0.008%

    No Known Activations