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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    1.11
    whitelist
    1.01
    views
    0.88
    teachers
    0.82
    ignore
    0.82
    ну
    0.81
    when
    0.75
     ці
    0.73
    лі
    0.73
    焼き
    0.72
    POSITIVE LOGITS
    ﺤ
    0.92
     Тыва
    0.76
    芰
    0.75
     بط
    0.74
    ITOR
    0.73
     Tuy
    0.73
    Etiam
    0.73
     destacan
    0.72
     inalámb
    0.71
    فن
    0.71
    Act Density 0.001%

    No Known Activations