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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Muchas
    0.67
    Hãy
    0.66
    Buenas
    0.64
     Kylie
    0.63
     humbly
    0.63
     Leia
    0.62
    Teen
    0.61
    हूं
    0.61
     Muchas
    0.60
     Muchos
    0.60
    POSITIVE LOGITS
    ↵
    0.69
     perturbative
    0.67
     discretization
    0.65
     perturbation
    0.61
     \
    0.59
    0.59
    0.59
    _{\
    0.58
     coalgebra
    0.58
     dipole
    0.58
    Act Density 0.000%

    No Known Activations