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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ft
    0.38
    ኮ
    0.37
     prefs
    0.35
    Call
    0.35
     Call
    0.34
     Bump
    0.34
    既
    0.34
     puno
    0.34
     ру
    0.34
    ża
    0.34
    POSITIVE LOGITS
     rica
    0.43
    oucher
    0.38
    rikan
    0.37
     ያ
    0.37
    ന്നി
    0.37
    分离
    0.37
     Primitive
    0.37
    rían
    0.36
    ष्मा
    0.36
    रिक्
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.