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

    Neuronpedia

    INDEX
    Explanations

    exclamations and strong language, particularly those using profanity or strong emotional expressions

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

    profanity and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.58
    둬
    -0.41
     Manfaat
    -0.41
     Bor
    -0.38
    ünstig
    -0.37
    iség
    -0.37
     Lingkungan
    -0.36
    secara
    -0.36
     Kele
    -0.36
    olat
    -0.36
    POSITIVE LOGITS
    ScopeManager
    0.61
    SourceChecksum
    0.59
    Personensuche
    0.59
    WriteTagHelper
    0.56
     OFDb
    0.54
    ConstraintMaker
    0.51
     CreateTagHelper
    0.48
     nahilalakip
    0.46
    Rhestr
    0.46
    AddTagHelper
    0.45
    Act Density 0.279%

    No Known Activations