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

    Neuronpedia

    INDEX
    Explanations

    setup and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proteins
    0.32
     hedges
    0.29
    proteins
    0.29
     fibrils
    0.28
     algebras
    0.28
     dyes
    0.28
     биологи
    0.28
     humoral
    0.28
     hormones
    0.27
     вещества
    0.27
    POSITIVE LOGITS
    点击
    0.41
     manually
    0.38
    打开
    0.37
    நீங்கள்
    0.36
    登录
    0.34
    手动
    0.34
    你需要
    0.34
     login
    0.33
    单击
    0.33
     Klik
    0.33
    Act Density 0.818%

    No Known Activations