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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     posteriores
    1.06
     privados
    1.06
     thaliana
    1.01
     haciendo
    0.99
     realizar
    0.98
     poniendo
    0.96
     realizando
    0.95
     pueda
    0.95
     anteriores
    0.94
     axiom
    0.94
    POSITIVE LOGITS
    er
    0.86
    i
    0.75
    ić
    0.71
    ه
    0.68
    ম
    0.63
     Melting
    0.62
     Wilk
    0.61
    kr
    0.61
    Wy
    0.61
    h
    0.60
    Act Density 0.000%

    No Known Activations