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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اینکه
    0.44
    ACCOUNT
    0.44
    _{\
    0.43
    keyDown
    0.43
     وعند
    0.43
     یک
    0.42
    subsection
    0.42
     אך
    0.42
    ನಾಟಕ
    0.41
    {
    0.41
    POSITIVE LOGITS
    대
    0.62
    ين
    0.59
     from
    0.55
    ла
    0.55
    et
    0.55
    da
    0.52
    ina
    0.50
    il
    0.49
    ل
    0.49
    ج
    0.49
    Act Density 0.461%

    No Known Activations