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

    Neuronpedia

    INDEX
    Explanations

    kingdoms, villages, cottages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دائو
    0.43
     Mok
    0.41
     Chir
    0.40
    നിര
    0.39
     цветов
    0.39
     Noh
    0.38
     chirp
    0.38
     ElevatedButton
    0.38
     prayed
    0.37
     CHIKV
    0.37
    POSITIVE LOGITS
     kingdom
    0.49
    kingdom
    0.43
     cottage
    0.42
     Messina
    0.42
     kingdoms
    0.41
    王国
    0.41
     Cottage
    0.41
     الملك
    0.41
     villages
    0.41
    village
    0.40
    Act Density 0.005%

    No Known Activations