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

    Neuronpedia

    INDEX
    Explanations

    zip, sync, drives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endpoint
    0.91
    immune
    0.90
    روط
    0.89
    comprom
    0.89
    }-(
    0.89
     بتاعت
    0.88
     doughnut
    0.87
     obje
    0.87
     doughnuts
    0.86
     autoc
    0.86
    POSITIVE LOGITS
    いった
    0.76
    事業
    0.74
     disebutkan
    0.69
    วิ
    0.69
    ダイ
    0.69
    ruari
    0.69
    forth
    0.69
    名
    0.68
    リスト
    0.68
    soever
    0.68
    Act Density 0.031%

    No Known Activations