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

    Neuronpedia

    INDEX
    Explanations

    desertification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     numéro
    0.78
    아
    0.78
     diretto
    0.77
     flusso
    0.76
     taglio
    0.76
    どう
    0.74
     pensato
    0.73
    ア
    0.72
     testaceis
    0.71
    iquée
    0.71
    POSITIVE LOGITS
     gobern
    0.86
    ians
    0.83
     již
    0.78
    ία
    0.76
     misfortunes
    0.76
    iędzy
    0.75
    ธุรก
    0.73
    iary
    0.72
    zhihu
    0.71
     sums
    0.71
    Act Density 0.002%

    No Known Activations