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

    Neuronpedia

    INDEX
    Explanations

    gratitude for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Avec
    0.37
     sempat
    0.36
    zt
    0.35
    Nya
    0.35
    Após
    0.35
     nhé
    0.34
    ുകൊണ്ടാണ്
    0.34
     engl
    0.34
     Após
    0.34
     âgé
    0.34
    POSITIVE LOGITS
    。『
    0.38
     detrimental
    0.38
     discernible
    0.38
    。「
    0.37
     intertwined
    0.36
    conversation
    0.36
    meldung
    0.36
    합니다
    0.35
    screens
    0.35
    pyrimidine
    0.35
    Act Density 0.001%

    No Known Activations