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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    g
    1.59
    CH
    1.52
    2
    1.52
    d
    1.44
    c
    1.44
    _
    1.42
    3
    1.39
    BA
    1.37
    t
    1.37
    '
    1.34
    POSITIVE LOGITS
    ین
    1.91
    ні
    1.49
    ン
    1.49
    ن
    1.34
    𝗻
    1.34
    न
    1.26
    یب
    1.25
     мира
    1.23
    きた
    1.22
    𝔪
    1.22
    Act Density 0.000%

    No Known Activations