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

    Neuronpedia

    INDEX
    Explanations

    semantic role labeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estyle
    0.42
     elef
    0.41
     etiquette
    0.40
    ಗಳಿವೆ
    0.40
     velv
    0.40
     Yogi
    0.40
     correctness
    0.39
    生成的
    0.39
     burlap
    0.39
    ニチイ
    0.39
    POSITIVE LOGITS
    Plug
    0.64
     Plug
    0.62
    Battery
    0.57
     plug
    0.56
     plugs
    0.54
     battery
    0.54
     Bluetooth
    0.53
     बैटरी
    0.53
    battery
    0.52
    Parts
    0.52
    Act Density 0.001%

    No Known Activations