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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    CTV
    0.93
    Veter
    0.91
    cri
    0.91
    Holland
    0.86
    Carm
    0.86
     Fehl
    0.86
    inflate
    0.84
     Eber
    0.84
    ⣤
    0.84
    Corn
    0.83
    POSITIVE LOGITS
     favored
    0.90
    theless
    0.87
     ano
    0.86
     favoured
    0.85
    akala
    0.84
    ango
    0.84
     apo
    0.83
    ATIONS
    0.83
    apo
    0.82
    ays
    0.82
    Act Density 0.000%

    No Known Activations