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

    Neuronpedia

    INDEX
    Explanations

    patterns and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     отка
    0.40
    मिटेड
    0.39
    isection
    0.38
    ตัด
    0.38
    忄
    0.38
    getStatusCode
    0.37
    屠
    0.37
    भो
    0.37
    ติด
    0.37
    Ruby
    0.37
    POSITIVE LOGITS
     patterns
    1.01
     relationships
    0.85
     Patterns
    0.85
    patterns
    0.84
    Patterns
    0.82
     patrones
    0.73
     pattern
    0.73
     correlations
    0.71
    relationships
    0.71
     패턴
    0.71
    Act Density 0.067%

    No Known Activations