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

    Neuronpedia

    INDEX
    Explanations

    Legibility, Quebec, Lek

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可以
    2.23
    Ա
    2.19
    ۹
    2.17
    在
    2.11
    েন
    2.08
    には
    2.08
    아야
    2.05
    在上
    2.03
    합니다
    1.91
    就
    1.90
    POSITIVE LOGITS
    iu
    2.55
    ii
    2.44
    iye
    2.42
    im
    2.36
    aan
    2.34
    esi
    2.33
    castle
    2.30
    db
    2.16
    iest
    2.16
    chen
    2.09
    Act Density 0.072%

    No Known Activations