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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    被æĬĵ
    -0.33
    çļĦèĦ¸
    -0.28
    orum
    -0.28
    ocs
    -0.26
    ioned
    -0.26
    aux
    -0.25
    .newaxis
    -0.25
    Schedulers
    -0.24
    è°ģçŁ¥
    -0.24
     hail
    -0.24
    POSITIVE LOGITS
    æ¯ĶèµĽ
    0.27
    åIJĮæŶ
    0.26
    _DOM
    0.25
    myp
    0.25
    istr
    0.24
     Tol
    0.24
    Rem
    0.24
     Barr
    0.24
    èŀį
    0.24
    ific
    0.23
    Act Density 4.776%

    No Known Activations