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

    Neuronpedia

    INDEX
    Explanations

    main idea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     d
    0.55
    _{
    0.53
    {#
    0.53
     questions
    0.52
    Gh
    0.50
    ッシュ
    0.50
    ناصر
    0.50
    simple
    0.48
    Ra
    0.48
    気を
    0.48
    POSITIVE LOGITS
     સ્ટો
    0.58
    bestroute
    0.55
     બે
    0.55
    ísmo
    0.55
     Doremi
    0.54
     এক
    0.53
     reciben
    0.52
     betrayed
    0.52
     Би
    0.52
     অবস্থিত
    0.51
    Act Density 0.028%

    No Known Activations