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

    Neuronpedia

    INDEX
    Explanations

    Can we explore implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     également
    0.38
     ,
    0.32
     considere
    0.31
     Jacks
    0.31
     Conversely
    0.30
    dbp
    0.29
     requiring
    0.29
    ieson
    0.29
    np
    0.28
    ுண்டு
    0.28
    POSITIVE LOGITS
    很
    0.36
    хий
    0.34
     increíble
    0.34
     traz
    0.34
    ЛИ
    0.33
    י
    0.33
    穩定
    0.33
     História
    0.33
    මෙ
    0.33
    この
    0.32
    Act Density 0.039%

    No Known Activations