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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     blot
    0.74
    д
    0.70
     frown
    0.68
     add
    0.67
    ors
    0.66
    Add
    0.65
    add
    0.64
     global
    0.64
    د
    0.63
     tolerance
    0.62
    POSITIVE LOGITS
     historische
    1.03
    ⃖
    0.93
    glichkeiten
    0.93
     vrijdag
    0.89
     technische
    0.88
     erforderlich
    0.87
     propriedade
    0.87
     erfolgreich
    0.86
     niemals
    0.86
    lcc
    0.86
    Act Density 0.000%

    No Known Activations