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

    Neuronpedia

    INDEX
    Explanations

    neuroscience and discoveries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    カスタ
    0.48
    nement
    0.46
    ॅप
    0.43
    ॅन
    0.42
     druž
    0.42
    נים
    0.42
    共
    0.42
     Azul
    0.41
    u
    0.41
    வல்
    0.41
    POSITIVE LOGITS
     判断
    0.48
     interprets
    0.46
     discoveries
    0.45
     backups
    0.44
     သိ
    0.43
     лечения
    0.42
    သိ
    0.39
     обнаружи
    0.39
     discovers
    0.38
     verrez
    0.38
    Act Density 0.002%

    No Known Activations