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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific events or announcements

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

    new content, replace, listen, strong, level, understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     olympiques
    -0.48
    chery
    -0.46
    iduous
    -0.46
    تيجة
    -0.45
     Whisky
    -0.45
     whisky
    -0.45
    berra
    -0.44
    ymce
    -0.44
    annique
    -0.44
    becue
    -0.44
    POSITIVE LOGITS
    StoryboardSegue
    0.60
    NameInMap
    0.56
     utilizing
    0.53
    MessageOf
    0.52
     Utilizing
    0.52
    Utiliz
    0.48
     typelib
    0.47
    ReusableCell
    0.47
     mergeFrom
    0.47
     Numerade
    0.45
    Act Density 0.042%

    No Known Activations