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

    Neuronpedia

    INDEX
    Explanations

    SAMHSA, Bloomberg, Behind the Name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Swagger
    0.75
    Comments
    0.69
    lite
    0.64
    Shop
    0.62
     app
    0.61
     ->
    0.61
     prvo
    0.61
     Comments
    0.60
    webapp
    0.60
    Commenting
    0.60
    POSITIVE LOGITS
    ॑
    0.67
     thc
    0.64
     ofthe
    0.61
     …,
    0.60
    ⼤
    0.59
    毉
    0.58
    тата
    0.58
    अर्थ
    0.58
     উত্প
    0.56
     leftist
    0.56
    Act Density 0.119%

    No Known Activations