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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    duction
    0.45
    Rush
    0.42
    hydration
    0.39
     Shred
    0.39
    estand
    0.38
    pont
    0.38
    пусти
    0.37
    ሮ
    0.36
    renees
    0.36
    бенок
    0.35
    POSITIVE LOGITS
     kol
    0.44
    یکل
    0.42
     teks
    0.39
     왼
    0.38
     middlemen
    0.38
     subi
    0.38
     required
    0.38
     bank
    0.38
    ोबर
    0.38
    came
    0.38
    Act Density 0.000%

    No Known Activations