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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ان
    1.41
     teorías
    1.37
    يال
    1.29
     ontwikk
    1.27
     sizlerle
    1.27
    راہیم
    1.26
    ేక
    1.26
    ი
    1.26
    ള്‍
    1.22
    Hace
    1.21
    POSITIVE LOGITS
     проис
    1.01
    threatening
    1.00
    pa
    0.96
     biar
    0.91
    re
    0.91
    w
    0.90
    radical
    0.89
    ainen
    0.88
     않았
    0.87
     radical
    0.86
    Act Density 0.000%

    No Known Activations