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

    Neuronpedia

    INDEX
    Explanations

    min, misconfigurations, min-max scaling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.93
    ل
    0.82
    el
    0.80
    न
    0.79
    л
    0.79
    لى
    0.76
    한
    0.74
    mos
    0.72
    ittarius
    0.71
    MatContext
    0.71
    POSITIVE LOGITS
    3
    1.09
     depolar
    0.76
    {
    0.75
    AN
    0.72
    4
    0.72
    ]
    0.71
    ],
    0.70
    ারে
    0.70
    (
    0.69
    াজ
    0.69
    Act Density 0.055%

    No Known Activations