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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lerde
    -0.07
    autoreleasepool
    -0.07
    роме
    -0.06
    する
    -0.06
    Türkiye
    -0.06
     weekend
    -0.06
    ?page
    -0.06
    因为
    -0.06
     travers
    -0.06
    很多
    -0.06
    POSITIVE LOGITS
    .readString
    0.06
     menacing
    0.06
    „N
    0.06
     页面
    0.06
     classy
    0.06
    Rejected
    0.06
    nginx
    0.06
     Computes
    0.06
    ГО
    0.06
     Restart
    0.06
    Act Density 0.002%

    No Known Activations