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

    Neuronpedia

    INDEX
    Explanations

    sections related to professional and academic backgrounds

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

    sources and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.59
    hyrchwyd
    -0.57
    GraphicsUnit
    -0.52
    SourceChecksum
    -0.51
     Administrativna
    -0.51
    EndGlobal
    -0.51
     AssemblyCulture
    -0.48
     препратки
    -0.47
     MainAxisSize
    -0.46
     Италијани
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.41
     فريبيس
    0.38
     langer
    0.36
    Hentet
    0.35
     purpose
    0.35
     buch
    0.34
     nahilalakip
    0.34
    0.34
    ⎣
    0.34
     uns
    0.34
    Act Density 0.079%

    No Known Activations