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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Anime
    -0.06
     Witch
    -0.06
    Mil
    -0.06
     crying
    -0.06
     placing
    -0.06
     reveal
    -0.06
     hit
    -0.06
     chron
    -0.06
    　　 　
    -0.06
    nbr
    -0.06
    POSITIVE LOGITS
     ulaş
    0.07
    iyeti
    0.06
    western
    0.06
    //----------------
    0.06
    OPS
    0.06
     doprav
    0.06
    操作
    0.06
     dirent
    0.06
     nhắc
    0.06
    JNIEXPORT
    0.06
    Act Density 0.006%

    No Known Activations