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

    Neuronpedia

    INDEX
    Explanations

    application of techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    قع
    0.65
    Hosting
    0.65
    Streaming
    0.64
    দের
    0.63
    ょう
    0.62
    Hover
    0.61
    Лі
    0.61
    环境中
    0.61
    networks
    0.60
    程度の
    0.60
    POSITIVE LOGITS
     employed
    1.10
     devised
    0.95
     adopted
    0.92
     developed
    0.90
     diterapkan
    0.90
     применяется
    0.88
     pioneered
    0.88
     used
    0.85
    を採用
    0.85
     অবলম্বন
    0.84
    Act Density 0.779%

    No Known Activations