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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and variables used in theoretical contexts

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

    mathematical and code expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     them
    -0.42
    NameInMap
    -0.39
     cref
    -0.39
    GOTREF
    -0.37
    cloudflare
    -0.35
    هن
    -0.34
     vVar
    -0.34
    ward
    -0.33
    cels
    -0.32
    ibouti
    -0.32
    POSITIVE LOGITS
    HtmlAttribute
    0.71
    Personensuche
    0.63
    
    0.61
     Biôgrafia
    0.59
     InputDecoration
    0.57
    الدراسه
    0.56
     виправивши
    0.53
     ProtoMessage
    0.51
    SourceChecksum
    0.48
    CloseOperation
    0.47
    Act Density 0.880%

    No Known Activations