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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    л
    0.50
    다음
    0.44
     Bremer
    0.42
    孵
    0.42
    阻
    0.40
    南
    0.40
    남
    0.39
    온
    0.39
    窄
    0.39
    ిన
    0.39
    POSITIVE LOGITS
    emple
    0.53
    kere
    0.50
     Frente
    0.49
     भाभी
    0.49
    gota
    0.48
     haría
    0.48
    edì
    0.47
    razione
    0.47
    tama
    0.47
    bala
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.