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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical values related to specific types of data

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

    currency symbols, medical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rather
    -0.40
     foule
    -0.40
     Mati
    -0.40
     besti
    -0.39
    卑
    -0.38
     indeed
    -0.37
     Indeed
    -0.35
    حي
    -0.35
    Balas
    -0.35
     intellig
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    0.68
    :✨
    0.66
     autorytatywna
    0.63
    +#+#
    0.54
    󠁣
    0.54
    rlpool
    0.53
     Мексичка
    0.52
    StoryboardSegue
    0.51
    TypedDataSet
    0.51
    makeText
    0.51
    Act Density 0.049%

    No Known Activations