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

    Neuronpedia

    INDEX
    Explanations

    depth limit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    দ্ধ
    0.40
     حجم
    0.38
    種類の
    0.38
     COP
    0.37
     warten
    0.37
     верхней
    0.37
     Volumen
    0.37
    VOLUME
    0.35
     tamaños
    0.35
     сверху
    0.35
    POSITIVE LOGITS
     multilevel
    0.44
     directory
    0.43
     स्तर
    0.43
     directories
    0.43
     shallow
    0.41
    二级
    0.41
    rophication
    0.40
    shallow
    0.40
    最多
    0.40
     genealogy
    0.40
    Act Density 0.006%

    No Known Activations