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

    Neuronpedia

    INDEX
    Explanations

    and or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UIServer
    0.25
    ují
    0.24
    elenggarakan
    0.24
    َيْ
    0.23
    📂
    0.23
    ávají
    0.22
    issä
    0.22
     gewährleisten
    0.22
    ụng
    0.22
    <unused2138>
    0.22
    POSITIVE LOGITS
     a
    0.44
     the
    0.34
     an
    0.33
    /
    0.29
     its
    0.28
     some
    0.26
     n
    0.25
     various
    0.24
     another
    0.23
     consequent
    0.23
    Act Density 0.667%

    No Known Activations