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

    Neuronpedia

    INDEX
    Explanations

    Code/Licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Boeh
    -0.27
    ç¥ŀç§ĺ
    -0.25
    Pen
    -0.25
    æİ¥åıĹäºĨ
    -0.25
    UnitOfWork
    -0.24
    dal
    -0.24
    менÑĤ
    -0.24
    bard
    -0.24
    Tokenizer
    -0.24
    ä¸Ĭè°ĥ
    -0.24
    POSITIVE LOGITS
    <Result
    0.29
    ĪæĿĥ
    0.28
    åĪĻ
    0.28
    inho
    0.27
    è·Ŀ
    0.27
     favourite
    0.26
    åį°
    0.26
     argue
    0.26
    常
    0.24
     Gron
    0.24
    Act Density 0.001%

    No Known Activations