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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or affirmation

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

    well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HomeAsUpEnabled
    -0.58
    Manbalar
    -0.57
    ביוגרפיה
    -0.56
    ExtendWith
    -0.56
     يتيمه
    -0.55
     nahilalakip
    -0.54
     оригіналу
    -0.53
    OGND
    -0.52
     TextAppearance
    -0.50
     createSlice
    -0.50
    POSITIVE LOGITS
     mundiales
    0.47
    big
    0.45
     asimismo
    0.44
     competir
    0.43
     gitu
    0.42
     competitivo
    0.42
     certamen
    0.42
     competição
    0.41
     Presidencia
    0.41
     consommation
    0.41
    Act Density 0.018%

    No Known Activations