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

    Neuronpedia

    INDEX
    Explanations

    metal residue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mier
    0.95
    ET
    0.91
    BA
    0.89
    ър
    0.88
     musia
    0.84
    ğer
    0.82
     chodzi
    0.79
    وک
    0.79
    将
    0.79
    នឹង
    0.78
    POSITIVE LOGITS
    ている
    1.00
    了一声
    0.89
    imentary
    0.88
    utives
    0.82
    ian
    0.81
    itons
    0.81
     कॉस
    0.80
     an
    0.80
    しい
    0.80
    ی
    0.80
    Act Density 0.001%

    No Known Activations