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

    Neuronpedia

    INDEX
    Explanations

    project structure files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     macrophage
    0.46
     snelheid
    0.44
    giveness
    0.42
     culo
    0.41
     extingu
    0.41
    طع
    0.40
     discoloration
    0.40
     discharge
    0.39
     adhesions
    0.39
     obstetric
    0.39
    POSITIVE LOGITS
    ├──
    0.63
    文件夹
    0.61
     Dateien
    0.59
    文件
    0.57
    檔案
    0.57
     файлы
    0.56
    目录
    0.56
     文件
    0.55
    结构
    0.55
     archivos
    0.54
    Act Density 0.124%

    No Known Activations