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

    Neuronpedia

    INDEX
    Explanations

    Donald Trump

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     повышение
    0.42
    蟋
    0.42
    াৰ
    0.41
     предложение
    0.40
    옌
    0.40
    >≥</
    0.39
    会場
    0.39
     CALCUL
    0.38
    ப்பட்டுள்ள
    0.37
     AMD
    0.37
    POSITIVE LOGITS
     tradition
    0.45
     keeps
    0.43
     karyawan
    0.41
     celebs
    0.41
     گستر
    0.40
     یہودی
    0.40
    ihanna
    0.40
     motorist
    0.40
     shopper
    0.39
     drawer
    0.39
    Act Density 0.001%

    No Known Activations