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

    Neuronpedia

    INDEX
    Explanations

    large language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     {@
    0.53
    omitempty
    0.50
     \|\
    0.50
    ঙ্গের
    0.49
    LastGenOutput
    0.49
     ниже
    0.48
     {\
    0.47
    网址
    0.47
     camadas
    0.47
    Encript
    0.47
    POSITIVE LOGITS
     इंट्रोडक्शन
    0.47
    かし
    0.46
     দুর্নীতি
    0.46
     nhá
    0.46
     పాటు
    0.44
     podrás
    0.44
     proper
    0.44
     ड्रोन
    0.43
    も見
    0.43
     research
    0.42
    Act Density 0.846%

    No Known Activations