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

    Neuronpedia

    INDEX
    Explanations

    on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ىل
    0.77
     Terbaru
    0.75
    wrapper
    0.75
     criticizing
    0.74
    skjaer
    0.73
     Caught
    0.73
    Ƅ
    0.73
    িক্ষ
    0.72
     sagging
    0.72
    imageNamed
    0.72
    POSITIVE LOGITS
     paths
    0.71
    מ
    0.68
     estabele
    0.65
     takers
    0.65
     ramas
    0.64
     सम्
    0.63
     itineraries
    0.63
     funds
    0.63
     möjlig
    0.62
     altres
    0.62
    Act Density 0.001%

    No Known Activations