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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     buon
    0.51
    大概
    0.48
     aproximadamente
    0.45
     yaklaşık
    0.45
     approximately
    0.44
     أ
    0.44
     bahagian
    0.44
     deprive
    0.44
     bode
    0.43
     alors
    0.43
    POSITIVE LOGITS
    운데
    0.39
     calculator
    0.38
    astic
    0.37
    IsNot
    0.37
    icult
    0.36
    atha
    0.36
    㴼
    0.36
    ంబే
    0.36
    если
    0.36
     सोडा
    0.35
    Act Density 0.004%

    No Known Activations