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

    Neuronpedia

    INDEX
    Explanations

    Dijkstra algorithm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cauchy
    0.38
    ಡ
    0.37
     المثلث
    0.36
    opadhyay
    0.36
    اول
    0.36
    Fri
    0.36
     inoculum
    0.36
     triangulation
    0.35
     Proposed
    0.34
    MT
    0.34
    POSITIVE LOGITS
    ibas
    0.47
    iktok
    0.46
     Straw
    0.43
    stra
    0.42
     ಸುದ್ದ
    0.40
    navigateTo
    0.40
    िक्स
    0.39
    ora
    0.38
     राइ
    0.38
    Straw
    0.38
    Act Density 0.002%

    No Known Activations