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

    Neuronpedia

    INDEX
    Explanations

    writing systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्रण
    -0.06
    ้ำหน
    -0.06
    ultimo
    -0.06
     الحديث
    -0.06
    _des
    -0.05
     strongest
    -0.05
    кі
    -0.05
    BUTTON
    -0.05
     merit
    -0.05
    �
    -0.05
    POSITIVE LOGITS
     BLL
    0.08
    �
    0.07
     ';↵↵
    0.07
    ↵    ↵    ↵
    0.07
     reconnaissance
    0.07
     rửa
    0.06
    _contin
    0.06
    름
    0.06
    ';↵↵
    0.06
    ',↵
    0.06
    Act Density 0.013%

    No Known Activations