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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performing actions or tasks

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

    Comes before "to do this" or "to do so"

    np_acts-logits-general · gemini-2.0-flash

    introducing explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.54
    CreateMap
    -0.50
    CultureInfo
    -0.49
    izable
    -0.49
     незавершена
    -0.48
    исленность
    -0.48
     Propri
    -0.47
     spar
    -0.46
     repres
    -0.45
    Становништво
    -0.45
    POSITIVE LOGITS
     acest
    0.48
     particulières
    0.48
     zijne
    0.47
    autaire
    0.45
     vectorielle
    0.45
     CreateTagHelper
    0.45
     solches
    0.44
     pédagogique
    0.43
     dergleichen
    0.43
     étoient
    0.43
    Act Density 0.600%

    No Known Activations