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

    Neuronpedia

    INDEX
    Explanations

    URLs in quotes or brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    렇
    0.33
    Hosted
    0.33
     terecht
    0.32
    وئ
    0.32
     Collaboration
    0.32
    ቒ
    0.32
     dédi
    0.31
     tôi
    0.31
     الاق
    0.31
     আমায়
    0.31
    POSITIVE LOGITS
    https
    0.59
    http
    0.56
     https
    0.50
     ../
    0.46
     http
    0.46
    mongodb
    0.39
    IPAL
    0.37
    mailto
    0.36
    ...");
    0.36
    xmlns
    0.36
    Act Density 0.006%

    No Known Activations