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

    Neuronpedia

    INDEX
    Explanations

    undefined memory or variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rivers
    0.37
    鏁
    0.37
    operators
    0.37
    enterprise
    0.35
    aranteed
    0.35
    jou
    0.35
    မ
    0.35
    અ
    0.35
    omatic
    0.34
    かう
    0.34
    POSITIVE LOGITS
     frameborder
    0.42
     смы
    0.39
     Hauser
    0.38
    twig
    0.37
     AppModule
    0.36
     Va
    0.35
     सहज
    0.35
     recital
    0.35
     http
    0.35
     limpi
    0.35
    Act Density 0.000%

    No Known Activations