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

    Neuronpedia

    INDEX
    Explanations

    pa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arke
    0.39
     '%'
    0.39
    arne
    0.38
    Ara
    0.38
    йдет
    0.37
     Urb
    0.36
    Slide
    0.36
    hme
    0.36
     ARA
    0.36
    %"
    0.36
    POSITIVE LOGITS
     pa
    0.68
    pa
    0.55
     PA
    0.55
     па
    0.49
     pá
    0.47
    PA
    0.45
     Pa
    0.44
     interests
    0.43
    パ
    0.43
    oo
    0.43
    Act Density 0.006%

    No Known Activations