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

    Neuronpedia

    INDEX
    Explanations

    writing from scratch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '")
    0.34
     цієї
    0.34
     этих
    0.33
    ในการ
    0.33
    #:
    0.32
     సినిమాలో
    0.32
    ާތ
    0.31
     स्ने
    0.30
    ✻
    0.30
     ගත
    0.30
    POSITIVE LOGITS
     anew
    0.33
    on
    0.32
     ag
    0.30
    p
    0.30
     p
    0.29
     new
    0.28
     thoughtful
    0.28
    л
    0.28
     n
    0.28
     thoughtfully
    0.27
    Act Density 0.040%

    No Known Activations