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

    Neuronpedia

    INDEX
    Explanations

    neural networks or parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ান্তে
    0.41
    Attempt
    0.38
    ALWAYS
    0.37
    兩種
    0.37
    Recover
    0.36
     Attempt
    0.35
    XIII
    0.35
    عدة
    0.35
     demo
    0.35
    िनय
    0.35
    POSITIVE LOGITS
    తున్నారు
    0.42
    읊
    0.40
     Mous
    0.38
     бү
    0.38
    ♥♥
    0.37
    ეგისტრ
    0.37
    㐌
    0.36
     የሆነ
    0.36
    áneas
    0.36
     subtree
    0.36
    Act Density 0.000%

    No Known Activations