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

    Neuronpedia

    INDEX
    Explanations

    references to academic or biographical resources

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

    encyclopedia and reference works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    能
    -0.38
     twist
    -0.38
     tin
    -0.36
    incen
    -0.35
     AppCompat
    -0.35
     Schrader
    -0.35
     mö
    -0.35
     rec
    -0.35
     عد
    -0.34
    authier
    -0.34
    POSITIVE LOGITS
    annica
    0.84
     okuyayım
    0.75
    ksikon
    0.62
    Personendaten
    0.60
    клопе
    0.60
     Italijanski
    0.58
    httphttps
    0.55
     autorytatywna
    0.53
     للاسماء
    0.52
     Италијани
    0.52
    Act Density 0.008%

    No Known Activations