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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     signUp
    -0.06
    �s
    -0.06
    Ў
    -0.06
     `[
    -0.06
     Ngày
    -0.06
    --)
↵
    -0.06
       
↵
    -0.06
     bishops
    -0.06
    ровать
    -0.06
    าน
    -0.06
    POSITIVE LOGITS
     locking
    0.07
     owl
    0.07
     market
    0.07
    actic
    0.07
     candidate
    0.07
    좌
    0.07
    madı
    0.07
     Highlander
    0.06
    execution
    0.06
    CTSTR
    0.06
    Act Density 0.003%

    No Known Activations