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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     possibile
    0.87
     solito
    0.82
     manten
    0.79
     secondo
    0.77
     paréntesis
    0.77
    पीड़न
    0.75
     bouillon
    0.75
     👌
    0.73
     plabic
    0.73
     quella
    0.72
    POSITIVE LOGITS
    og
    0.89
    aj
    0.87
    ok
    0.86
    1
    0.83
    8
    0.81
    ars
    0.78
    ำ
    0.77
    0
    0.76
    OR
    0.75
    5
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.