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

    Neuronpedia

    INDEX
    Explanations

    Explanations and reasons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     صالح
    -0.07
    416
    -0.06
     dizzy
    -0.06
     Ecuador
    -0.06
    ('\\
    -0.06
     Trails
    -0.06
     cocktail
    -0.06
     FF
    -0.06
     analyzer
    -0.06
     ků
    -0.06
    POSITIVE LOGITS
    률
    0.07
    attention
    0.06
    ussions
    0.06
    posed
    0.06
     поруш
    0.06
     synd
    0.06
    EventData
    0.06
    Wave
    0.06
     Pagination
    0.06
    phase
    0.06
    Act Density 0.045%

    No Known Activations