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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ле
    0.91
    ب
    0.80
     Flows
    0.74
    غ
    0.73
    اب
    0.73
    Examples
    0.70
    ло
    0.70
    Fixture
    0.69
    STS
    0.69
    But
    0.68
    POSITIVE LOGITS
    ijker
    0.87
     overseas
    0.86
     creation
    0.82
     appetizers
    0.82
    ⿵
    0.82
     spicy
    0.82
     rehabilitation
    0.81
     incarcer
    0.81
     newsletters
    0.81
     hydrazine
    0.81
    Act Density 0.000%

    No Known Activations