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

    Neuronpedia

    INDEX
    Explanations

    window dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imaged
    0.42
     hd
    0.42
    hd
    0.38
     plotted
    0.38
    flu
    0.37
     cinema
    0.37
     souvenirs
    0.37
     images
    0.37
     hb
    0.37
    gold
    0.36
    POSITIVE LOGITS
     ৪০০
    0.46
    实习
    0.45
    三百
    0.42
    ıntı
    0.41
    Resizable
    0.40
     ৩০০
    0.40
     окно
    0.40
    ágico
    0.39
     желательно
    0.39
     🌱
    0.39
    Act Density 0.009%

    No Known Activations