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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    铄
    0.52
     dici
    0.48
    c
    0.48
     principalement
    0.46
     coal
    0.46
    iberg
    0.46
     Central
    0.45
     Cir
    0.45
     perspectivas
    0.43
     play
    0.43
    POSITIVE LOGITS
    LE
    0.55
    KIS
    0.54
    KINS
    0.53
    KIA
    0.51
     อยู่
    0.51
    KOV
    0.50
     নেয়ার
    0.49
    ‬‬
    0.48
    KV
    0.47
    ĝ
    0.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.