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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     unresponsive
    0.67
     de
    0.66
     grounds
    0.63
     repaid
    0.62
     Marlowe
    0.60
     Liss
    0.60
    पूर्ति
    0.60
    
    0.59
     De
    0.59
     served
    0.58
    POSITIVE LOGITS
     அப்ப
    0.64
     καθη
    0.60
    HOOK
    0.59
    urée
    0.59
    Interpreter
    0.59
    var
    0.57
    istu
    0.57
    es
    0.56
    Hooks
    0.56
    чиков
    0.55
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.