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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    trzymać
    -0.07
    spo
    -0.07
    出发
    -0.07
     sebagai
    -0.07
     spaceship
    -0.07
    צא
    -0.07
    generated
    -0.07
     swallowed
    -0.07
    upper
    -0.07
     Usuario
    -0.07
    POSITIVE LOGITS
    峄
    0.07
    _HI
    0.07
     liệt
    0.07
    moon
    0.07
    Ӏ
    0.07
    ᡤ
    0.06
     реб
    0.06
     HI
    0.06
     nitrogen
    0.06
     Minuten
    0.06
    Act Density 0.047%

    No Known Activations