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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    0.83
    lilik
    0.79
    lular
    0.79
    িনবার্গ
    0.78
     х
    0.76
    ﻤ
    0.74
    ﻊ
    0.74
    ﺒ
    0.73
     ۹
    0.73
    ᱮ
    0.73
    POSITIVE LOGITS
    ס
    1.47
    س
    1.26
    с
    1.14
     Based
    1.12
    มัน
    1.05
    ’
    1.02
    '
    0.98
    ด
    0.98
    ت
    0.96
    :
    0.94
    Act Density 0.191%

    No Known Activations