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

    Neuronpedia

    INDEX
    Explanations

    feel natural

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     көзге
    0.42
     साजिश
    0.42
     Международ
    0.41
     monastic
    0.41
    対策
    0.40
    Former
    0.40
    させた
    0.40
     Ingeniería
    0.39
    expressing
    0.39
    ект
    0.39
    POSITIVE LOGITS
     pinc
    0.45
     consecutive
    0.43
     pano
    0.42
     responde
    0.42
     bear
    0.41
     fam
    0.40
     independ
    0.40
     respons
    0.40
    ède
    0.39
     dico
    0.39
    Act Density 0.001%

    No Known Activations