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

    Neuronpedia

    INDEX
    Explanations

    import tqdm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    हाना
    0.44
     carcinoma
    0.41
    ♝
    0.41
     Nevada
    0.40
     caravans
    0.40
     pran
    0.39
     frustrations
    0.39
    𝐲
    0.39
     interruption
    0.39
     carav
    0.39
    POSITIVE LOGITS
    auto
    0.40
     этого
    0.39
     அவருடைய
    0.37
    this
    0.36
    Shel
    0.35
    自动
    0.35
     auto
    0.35
    자동
    0.33
    دست
    0.33
    Luke
    0.33
    Act Density 0.000%

    No Known Activations