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

    Neuronpedia

    INDEX
    Explanations

    relationship between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    1.10
    es
    1.04
    atil
    0.98
    ik
    0.95
    া
    0.91
    ur
    0.91
    াম
    0.90
    at
    0.88
    ع
    0.87
    ї
    0.86
    POSITIVE LOGITS
    relationship
    0.99
    맺
    0.95
     отно
    0.91
     relationship
    0.91
    Relationship
    0.89
     Relationship
    0.89
     ткань
    0.88
     iliş
    0.88
     рядом
    0.86
     برقرار
    0.82
    Act Density 0.195%

    No Known Activations