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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    """
    1.04
    #
    0.95
    <?
    0.91
    <!--
    0.88
    \[
    0.87
    ﺘ
    0.87
    0.85
    I
    0.84
    ﺒ
    0.84
    $$\
    0.83
    POSITIVE LOGITS
     korban
    1.03
    யின்
    0.91
     lumière
    0.91
    లోకి
    0.86
     kleinere
    0.86
     terminée
    0.84
     Dinosaur
    0.84
    膣
    0.84
     وجود
    0.84
    प्टन
    0.84
    Act Density 0.001%

    No Known Activations