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

    Neuronpedia

    INDEX
    Explanations

    software dependencies and versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ফে
    0.42
    Cardiac
    0.39
     עו
    0.39
     ಮಿಶ್ರ
    0.38
    ftÂ
    0.38
    Matt
    0.38
     {//
    0.38
    ﻒ
    0.38
    дження
    0.37
     [&](
    0.37
    POSITIVE LOGITS
    >=
    0.86
    ==
    0.75
    ]==
    0.68
     latest
    0.61
    latest
    0.59
    的版本
    0.56
     >=
    0.56
     version
    0.54
     versão
    0.54
     версии
    0.52
    Act Density 0.035%

    No Known Activations