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

    Neuronpedia

    INDEX
    Explanations

    ken followed by yan, zo, ji, jo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    к
    1.27
    т
    1.16
    ینگ
    1.14
    AT
    1.13
    to
    1.08
     It
    1.02
    ﻛ
    1.02
    ク
    1.00
    <0x0D>
    1.00
    ่า
    0.99
    POSITIVE LOGITS
    ;
    1.61
     ken
    1.38
     Ken
    1.34
    ה
    1.28
    Ken
    1.27
     l
    1.12
     KEN
    1.12
     t
    1.11
    จะ
    1.09
    $
    1.05
    Act Density 0.002%

    No Known Activations