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

    Neuronpedia

    INDEX
    Explanations

    influence on decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    үл
    0.43
     Groom
    0.37
    groom
    0.37
     Kxe
    0.35
    мпа
    0.35
    ავლ
    0.35
    й
    0.35
     зап
    0.34
    кия
    0.34
    wic
    0.34
    POSITIVE LOGITS
    CONCLUSIONS
    0.46
     рассказать
    0.46
    രാഷ്ട്ര
    0.45
     zaključ
    0.42
     quindi
    0.42
    Adri
    0.40
    সভাপতি
    0.39
    કમ
    0.39
    昊
    0.39
    ADOC
    0.39
    Act Density 0.000%

    No Known Activations