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

    Neuronpedia

    INDEX
    Explanations

    from a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ἆ
    0.52
    ਟਰ
    0.52
    乆
    0.50
    狯
    0.48
    搆
    0.48
    拶
    0.47
    λώ
    0.45
    ને
    0.45
    ㄗ
    0.45
    ⵚ
    0.45
    POSITIVE LOGITS
     في
    0.54
    Landscape
    0.52
     in
    0.50
     در
    0.50
    city
    0.50
    ];
    0.45
    );
    0.44
     المد
    0.44
     مد
    0.43
     Regional
    0.43
    Act Density 0.000%

    No Known Activations