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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    必ず
    1.17
     horizont
    0.98
    꼭
    0.96
     wield
    0.92
    𝙃
    0.89
     polos
    0.88
    于
    0.87
     isotropy
    0.87
    Ꮃ
    0.87
     prong
    0.85
    POSITIVE LOGITS
    랙
    1.12
    lerdir
    1.11
     podendo
    1.04
    러스
    1.03
     Fransa
    1.03
    ngày
    1.03
     چکے
    1.02
    бо
    1.02
     Colombia
    1.00
     repudiandae
    1.00
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.