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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    '
    1.39
    )
    1.02
     I
    0.86
    \
    0.85
    ↵
    0.84
    ]
    0.84
     पंजीकरण
    0.81
    }
    0.78
     ที่
    0.77
    hopper
    0.75
    POSITIVE LOGITS
    ל
    1.62
    ল
    1.59
    ס
    1.53
    ون
    1.48
    ن
    1.48
    ز
    1.44
    ल
    1.40
    न
    1.39
    ב
    1.34
    ח
    1.33
    Act Density 0.000%

    No Known Activations