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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    y
    0.60
    z
    0.51
     Spare
    0.49
    はこの
    0.46
    з
    0.46
     abol
    0.46
     Mostly
    0.46
     Instal
    0.46
     Adequate
    0.46
     Perg
    0.45
    POSITIVE LOGITS
    ти
    0.57
    変わ
    0.52
     milik
    0.49
    ো
    0.49
    “[
    0.48
    гана
    0.48
     veces
    0.48
    ли
    0.47
     millones
    0.47
    登場
    0.46
    Act Density 0.104%

    No Known Activations