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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    These
    0.70
     These
    0.63
    列表
    0.63
     Lists
    0.63
    ت
    0.63
    They
    0.63
    這種
    0.61
    Это
    0.59
    Sounds
    0.59
    다
    0.58
    POSITIVE LOGITS
     and
    0.69
     semblance
    0.67
     groundwork
    0.64
     majest
    0.64
     terroir
    0.61
     inici
    0.61
     treasury
    0.61
     selves
    0.61
     zwią
    0.60
     intervention
    0.60
    Act Density 0.000%

    No Known Activations