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

    Neuronpedia

    INDEX
    Explanations

    UI / code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chalk
    0.79
    sixth
    0.78
     ஆற
    0.77
    mapi
    0.76
    MAG
    0.75
     நான
    0.75
    chalk
    0.74
    ৬
    0.74
     chalk
    0.74
    fourth
    0.74
    POSITIVE LOGITS
     çıktı
    0.67
     çıkt
    0.63
     Goodman
    0.63
     Linh
    0.62
    лык
    0.62
     ong
    0.62
    னுடைய
    0.60
    晶
    0.59
     alamat
    0.58
     kurang
    0.58
    Act Density 0.000%

    No Known Activations