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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     or
    -2.88
     или
    -1.93
    或
    -1.59
     atau
    -1.58
     eller
    -1.56
     hoặc
    -1.48
    或者
    -1.44
    หรือ
    -1.40
     nebo
    -1.38
     یا
    -1.37
    POSITIVE LOGITS
     Monfieur
    1.15
     myſelf
    1.05
     Jefus
    1.05
     ſeveral
    1.05
     houſe
    1.02
     pleaſure
    1.02
     purpoſe
    1.02
     ſmall
    1.01
     ſtate
    1.00
     Theſe
    0.99
    Act Density 0.285%

    No Known Activations