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

    Neuronpedia

    INDEX
    Explanations

    explaining a term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     எனப்படும்
    0.48
    knie
    0.45
    messages
    0.45
    ething
    0.44
    cin
    0.44
     mensajes
    0.44
    aston
    0.43
     odpowiedzi
    0.43
     удаления
    0.43
    দ্য
    0.42
    POSITIVE LOGITS
     “
    0.43
     ‘
    0.39
     sustainability
    0.39
     USED
    0.39
     Holocaust
    0.38
     پیسہ
    0.38
     dysplasia
    0.38
    ائيل
    0.37
     borders
    0.37
     term
    0.36
    Act Density 0.107%

    No Known Activations