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

    Neuronpedia

    INDEX
    Explanations

    scientific data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alpha
    -0.07
    Track
    -0.07
    _BOX
    -0.07
    ि,
    -0.07
     titles
    -0.07
     Close
    -0.07
     Track
    -0.06
    ĩ
    -0.06
     Resist
    -0.06
     edecek
    -0.06
    POSITIVE LOGITS
    руж
    0.07
    _PROF
    0.07
    シー
    0.06
    ARRIER
    0.06
    .central
    0.06
    خط
    0.06
     исход
    0.06
    _CONFIRM
    0.06
    roupon
    0.06
    _MA
    0.06
    Act Density 0.128%

    No Known Activations