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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уючи
    -0.07
    wor
    -0.06
    Tre
    -0.06
    _lens
    -0.06
     FileSystem
    -0.06
    _io
    -0.06
    ourses
    -0.06
     pairwise
    -0.06
    ection
    -0.06
    /common
    -0.06
    POSITIVE LOGITS
     تهران
    0.07
    จะม
    0.06
    นาง
    0.06
     İzmir
    0.06
    ｿ
    0.06
    .MapPath
    0.06
    抓
    0.06
     olmasına
    0.06
     philippines
    0.06
     commuting
    0.06
    Act Density 0.011%

    No Known Activations