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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    vect
    0.39
    coded
    0.39
    ঠিত
    0.38
     목적
    0.38
    Alignment
    0.37
     wrote
    0.37
     заб
    0.37
     неза
    0.36
    czych
    0.36
    ϳ
    0.36
    POSITIVE LOGITS
    nob
    0.41
     tom
    0.40
     overlaps
    0.39
    癒
    0.37
    umma
    0.36
    仕様
    0.35
     overlapped
    0.35
     thủ
    0.35
     उम
    0.35
     individ
    0.34
    Act Density 0.302%

    No Known Activations