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

    Neuronpedia

    INDEX
    Explanations

    telegram and operating systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    तुर
    0.48
    ጃ
    0.45
    पुट
    0.44
    रविवार
    0.43
     ಸಾವಿರ
    0.41
     주인
    0.40
    壽
    0.40
     शहरी
    0.40
    姥
    0.40
     이해
    0.40
    POSITIVE LOGITS
    Arch
    0.48
    .)
    0.45
    Attachments
    0.42
    dba
    0.42
    BD
    0.42
     SMA
    0.42
    kis
    0.40
    .),
    0.39
    .]
    0.39
    )
    0.38
    Act Density 0.000%

    No Known Activations