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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("../../
    -0.07
     Att
    -0.07
     الوقت
    -0.07
    well
    -0.06
     Guard
    -0.06
    Que
    -0.06
    ụ
    -0.06
    izada
    -0.06
    .app
    -0.06
    ('../../
    -0.06
    POSITIVE LOGITS
     frække
    0.07
     захист
    0.06
     blankets
    0.06
     dedim
    0.06
    小姐
    0.06
     fireworks
    0.06
     gbc
    0.06
     Giov
    0.06
     Hra
    0.06
     ribs
    0.06
    Act Density 0.010%

    No Known Activations