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

    Neuronpedia

    INDEX
    Explanations

    thank you for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.60
    E
    0.55
       
    0.50
     continues
    0.47
     requires
    0.46
    K
    0.46
    )).
    0.45
    LE
    0.45
    0
    0.45
    <0xB4>
    0.44
    POSITIVE LOGITS
    يل
    0.57
    បង្កើត
    0.52
    ကျ
    0.52
     decirlo
    0.48
     obeying
    0.48
    阍
    0.48
    偒
    0.48
     Chất
    0.47
     Comte
    0.47
     thấy
    0.47
    Act Density 0.006%

    No Known Activations