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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اين
    -0.08
    defines
    -0.07
     firstly
    -0.07
     yok
    -0.07
    03
    -0.06
    .fe
    -0.06
    nowledge
    -0.06
     Hispanic
    -0.06
     Hyderabad
    -0.06
    sess
    -0.06
    POSITIVE LOGITS
     endif
    0.06
     політи
    0.06
    -widgets
    0.06
    .prevent
    0.06
    \C
    0.06
     الاقتص
    0.06
     -----↵
    0.06
     fık
    0.06
     extern
    0.06
     µ
    0.06
    Act Density 0.042%

    No Known Activations