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

    Neuronpedia

    INDEX
    Explanations

    where followed by a noun/pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فى
    0.42
     Cuando
    0.42
     quando
    0.40
     cuando
    0.40
     When
    0.38
     ناحيه
    0.38
     എന്നാൽ
    0.38
     Unsere
    0.37
    '/
    0.36
     在
    0.36
    POSITIVE LOGITS
    abouts
    0.52
    ifrån
    0.42
    på
    0.39
    soever
    0.38
     কিনা
    0.38
    您可以
    0.37
    quiera
    0.37
    you
    0.37
    inafter
    0.37
    你可以
    0.36
    Act Density 0.024%

    No Known Activations