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

    Neuronpedia

    INDEX
    Explanations

    break down symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ձ
    0.49
     devemos
    0.48
    Wouldn
    0.47
    Você
    0.47
    鹖
    0.46
     échant
    0.45
    𒈗
    0.45
    ೆ
    0.44
    δε
    0.44
    פ
    0.44
    POSITIVE LOGITS
    rank
    0.50
     sixties
    0.48
     Fant
    0.47
    jo
    0.46
     Rank
    0.45
     Bibliothe
    0.44
    lee
    0.44
     Management
    0.44
    ’
    0.44
     list
    0.44
    Act Density 0.001%

    No Known Activations