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

    Neuronpedia

    INDEX
    Explanations

    you tell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2.42
    2
    1.37
    5
    1.30
    1
    1.29
     a
    1.23
    0
    1.20
    3
    1.19
    7
    1.19
    4
    1.18
    ל
    1.17
    POSITIVE LOGITS
    ズム
    1.14
    ‌,
    1.10
    ులు
    1.05
    adple
    1.05
    infodisc
    1.04
    ന്ഥ
    1.04
    ,‎
    1.02
     Владими
    1.01
    ग्विजय
    1.00
    зацию
    0.98
    Act Density 0.379%

    No Known Activations