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

    Neuronpedia

    INDEX
    Explanations

    foreign languages or specific jargon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৃ
    0.47
     components
    0.43
     warned
    0.43
     synonyms
    0.42
     administration
    0.42
     orthodont
    0.42
     luxuries
    0.41
    ឯ
    0.40
     primitives
    0.40
     administering
    0.40
    POSITIVE LOGITS
    ivez
    0.59
    vaa
    0.48
     יי
    0.46
    ât
    0.44
    rizioni
    0.44
     الحد
    0.43
     المج
    0.43
    IFE
    0.42
     voj
    0.42
    倞
    0.42
    Act Density 0.003%

    No Known Activations