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

    Neuronpedia

    INDEX
    Explanations

    weight inclusivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undeveloped
    0.41
    Magento
    0.39
     uninter
    0.39
    ন্দ্র
    0.38
     anlay
    0.38
    舧
    0.38
     बाधा
    0.38
     ir
    0.37
    經過
    0.36
    ധികം
    0.36
    POSITIVE LOGITS
     Soh
    0.45
     campus
    0.44
     Campus
    0.44
    Message
    0.43
    Campus
    0.43
    Poisson
    0.43
     कैंपस
    0.42
     Message
    0.40
     बलों
    0.40
     Northwestern
    0.40
    Act Density 0.000%

    No Known Activations