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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    า
    1.20
    یم
    1.18
    ות
    1.10
    я
    1.08
    ல்
    1.06
    ور
    1.05
    ą
    1.02
    ור
    0.99
    ים
    0.96
    い
    0.91
    POSITIVE LOGITS
    '
    1.19
    for
    1.16
    l
    1.09
    an
    1.04
    i
    1.03
    _
    1.02
    water
    0.95
    am
    0.93
    t
    0.91
    h
    0.91
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.