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

    Neuronpedia

    INDEX
    Explanations

    Server

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dedicated
    -1.01
     specialized
    -0.97
    dedicated
    -0.83
     special
    -0.82
    Dedicated
    -0.79
     dédié
    -0.78
     specialist
    -0.76
     Specialized
    -0.74
    Specialized
    -0.73
     specialised
    -0.73
    POSITIVE LOGITS
     Cæsar
    0.80
    ſelf
    0.76
     Anſ
    0.74
     Reſ
    0.73
    ьаж
    0.73
    hdashline
    0.72
     ་་
    0.72
     itſelf
    0.71
     незавершена
    0.71
     الدولى
    0.70
    Act Density 0.006%

    No Known Activations