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

    Neuronpedia

    INDEX
    Explanations

    instead or nope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    并将
    0.37
    !("{:
    0.36
    ambu
    0.36
    并
    0.34
    κό
    0.33
    ',)
    0.32
    임을
    0.31
     "):
    0.31
    ripciones
    0.31
     Рим
    0.31
    POSITIVE LOGITS
     Instead
    0.75
     instead
    0.71
    Instead
    0.59
    代わりに
    0.58
     invece
    0.57
    instead
    0.57
     вместо
    0.51
     nope
    0.50
     Nope
    0.48
     পরিবর্তে
    0.48
    Act Density 0.006%

    No Known Activations