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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases and transition words

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

    introducing explanations or observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    новништво
    -0.50
     ſur
    -0.43
     pleaſure
    -0.43
     perfons
    -0.42
     ſeveral
    -0.40
     houſe
    -0.39
     warszawa
    -0.39
     ſub
    -0.38
     Acton
    -0.38
    ChildScrollView
    -0.38
    POSITIVE LOGITS
    IUrlHelper
    0.47
    Viki
    0.43
    rungsseite
    0.43
    󠁮
    0.43
    kje
    0.43
     ayudarte
    0.42
     nahilalakip
    0.40
    ennifer
    0.40
    :✨
    0.40
     TAMBÉM
    0.40
    Act Density 0.577%

    No Known Activations