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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude and introductions in a formal context

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

    multiple languages and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.33
     hvě
    -0.33
     inspección
    -0.33
     ovlád
    -0.32
     naciones
    -0.32
     Begründung
    -0.31
     éduc
    -0.30
     bendera
    -0.30
     prodej
    -0.30
     rechange
    -0.30
    POSITIVE LOGITS
    Personensuche
    0.73
     Paglinawan
    0.65
     ErrIntOverflow
    0.63
     كومونز
    0.59
     betweenstory
    0.59
    Tembelea
    0.58
    ConstraintMaker
    0.58
    CloseOperation
    0.58
     defaultstate
    0.57
     okuyayım
    0.57
    Act Density 0.059%

    No Known Activations