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

    Neuronpedia

    INDEX
    Explanations

    community contribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मैंने
    0.45
     શક્ય
    0.44
     নিজেকে
    0.43
     নিজের
    0.41
    udent
    0.41
    几个
    0.41
     کئی
    0.41
    ]):
    0.41
    子
    0.40
     of
    0.40
    POSITIVE LOGITS
     membuatnya
    0.52
     তারাই
    0.48
     ją
    0.46
    帮你
    0.46
     इसे
    0.44
     цьому
    0.43
     તેને
    0.43
     themselves
    0.42
     intervened
    0.42
     hjäl
    0.41
    Act Density 0.096%

    No Known Activations