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

    Neuronpedia

    INDEX
    Explanations

    section after at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +](=
    0.45
     bimod
    0.44
     люби
    0.43
     прочита
    0.42
    વી
    0.42
    ▒
    0.41
    ંબ
    0.41
     لکھ
    0.40
    源代码
    0.39
    :
    0.39
    POSITIVE LOGITS
     pas
    0.45
     இவற்றை
    0.45
     to
    0.42
     before
    0.41
     when
    0.41
     அவற்றை
    0.41
    feu
    0.41
    なので
    0.40
    KPI
    0.40
    rcParams
    0.40
    Act Density 0.017%

    No Known Activations