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

    Neuronpedia

    INDEX
    Explanations

    less than symbols, typically used in comparison contexts or coding syntax

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

    loop initializations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tanleria
    -0.48
    
    -0.48
    wieś
    -0.47
    GEBURTS
    -0.47
     Мексичка
    -0.45
    ModelState
    -0.45
    SIG
    -0.44
    uxxxx
    -0.44
    BaseEntity
    -0.44
     QtWidgets
    -0.44
    POSITIVE LOGITS
     Länge
    0.49
     Fälle
    0.47
     Fläche
    0.47
     totalité
    0.46
     militer
    0.45
     INFORMACIÓN
    0.45
     TRABAJO
    0.45
     Tiefe
    0.45
     acuer
    0.44
     boyunca
    0.44
    Act Density 0.003%

    No Known Activations