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

    Neuronpedia

    INDEX
    Explanations

    video

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Controllers
    -0.07
    "]))↵
    -0.06
    _error
    -0.06
    )'↵
    -0.06
     Κο
    -0.06
     Lot
    -0.06
    .Cache
    -0.06
    imetype
    -0.06
    ellation
    -0.06
     Madame
    -0.06
    POSITIVE LOGITS
    พยาบาล
    0.07
    ра�
    0.07
     ง
    0.07
    EF
    0.06
     utiliz
    0.06
     hoặc
    0.06
     виб
    0.06
    .Generate
    0.06
    สว
    0.06
    didn
    0.06
    Act Density 0.006%

    No Known Activations