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

    Neuronpedia

    INDEX
    Explanations

    4K resolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.66
    ،
    0.62
     CERN
    0.61
    g
    0.60
     x
    0.59
     DJ
    0.57
     yester
    0.57
    ir
    0.57
     IBM
    0.57
    т
    0.55
    POSITIVE LOGITS
    ន
    0.57
    ],$
    0.53
    ]
    0.52
    টসম্যান
    0.49
    ំ
    0.49
    تما
    0.47
    屏
    0.46
    Situ
    0.46
     कीमतों
    0.46
    стью
    0.45
    Act Density 0.002%

    No Known Activations