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

    Neuronpedia

    INDEX
    Explanations

    carving and foreign scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     out
    0.45
    单一
    0.41
    Reprodu
    0.41
     дво
    0.40
     Gradle
    0.39
     jQuery
    0.39
    平成
    0.39
     JVM
    0.38
    nginx
    0.38
     VMs
    0.38
    POSITIVE LOGITS
    ียบ
    0.37
     carvings
    0.37
    
    0.37
    ល់
    0.36
    ズル
    0.36
     bay
    0.34
    続き
    0.33
     carving
    0.33
    ckenridge
    0.33
    نوان
    0.33
    Act Density 0.005%

    No Known Activations