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

    Neuronpedia

    INDEX
    Explanations

    really + intensifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یم
    1.50
    ނ
    1.27
    وک
    1.22
    𝘃
    1.20
    ೇ
    1.19
    dı
    1.16
    لک
    1.16
    𝓻
    1.14
    lara
    1.13
    𝗽
    1.13
    POSITIVE LOGITS
    ↵
    1.18
    ation
    1.13
    на
    0.97
    eth
    0.90
    จริง
    0.90
    ان
    0.88
    的核心
    0.87
    .
    0.87
    ம்
    0.86
    ↵↵
    0.85
    Act Density 0.100%

    No Known Activations