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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    9
    0.57
    8
    0.50
    uland
    0.48
    Angles
    0.47
    ooker
    0.47
    umping
    0.46
    ateboard
    0.46
    ufthansa
    0.45
    ashed
    0.45
    adese
    0.45
    POSITIVE LOGITS
    ın
    0.60
    लोग
    0.60
    ły
    0.53
     infringed
    0.51
    ω
    0.51
     kỹ
    0.50
     zyg
    0.50
    АК
    0.49
    ласти
    0.48
    ţii
    0.48
    Act Density 0.000%

    No Known Activations