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

    Neuronpedia

    INDEX
    Explanations

    foreign language texts or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Musical
    0.46
     спектак
    0.45
     Users
    0.42
     Musicians
    0.42
     Public
    0.41
     Surgery
    0.41
     Magical
    0.41
     Music
    0.40
    㷌
    0.40
    のマ
    0.39
    POSITIVE LOGITS
     dando
    0.46
     blobs
    0.46
    녓
    0.45
     gravité
    0.44
    zahlen
    0.44
     leurs
    0.43
     étaient
    0.42
     doba
    0.42
    olut
    0.42
     ihren
    0.41
    Act Density 0.004%

    No Known Activations