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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ingles
    0.79
     amigos
    0.77
     друзей
    0.75
     magnetores
    0.75
     anuncios
    0.73
    `,
    0.73
     osserv
    0.72
     frigor
    0.72
    [],
    0.71
     север
    0.71
    POSITIVE LOGITS
    rz
    0.74
    f
    0.73
    för
    0.70
    dare
    0.70
    河北
    0.69
    completely
    0.68
    能
    0.68
    ratio
    0.67
     طریق
    0.66
    謐
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.