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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    apa
    1.01
    ărilor
    1.00
    inger
    0.98
    ;
    0.97
    asjoner
    0.96
    กำ
    0.94
    ails
    0.94
    т
    0.94
    𝑒
    0.94
    𝙖
    0.93
    POSITIVE LOGITS
    yı
    1.29
    verts
    1.28
    dominal
    1.27
     resident
    1.27
     chuẩn
    1.26
    θεν
    1.24
    鸡
    1.23
    ות
    1.20
    деся
    1.20
     concentric
    1.19
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.