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

    Neuronpedia

    INDEX
    Explanations

    md

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apa
    -0.07
    プ
    -0.07
     ";"
    -0.07
     clothing
    -0.07
    -0.07
    -0.07
     AP
    -0.07
     temperatura
    -0.07
    _conversion
    -0.07
    eurs
    -0.06
    POSITIVE LOGITS
     televised
    0.07
     �
    0.06
    xD
    0.06
     एम
    0.06
     відбу
    0.06
     Μα
    0.06
     my
    0.06
     εμπ
    0.06
     sửa
    0.06
    Emer
    0.06
    Act Density 0.001%

    No Known Activations