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

    Neuronpedia

    INDEX
    Explanations

    forming, building, establishing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    0.36
    ও
    0.29
    كة
    0.26
    ków
    0.25
    </h2>
    0.25
    ın
    0.24
    ğı
    0.23
    féle
    0.23
    在
    0.23
    то
    0.23
    POSITIVE LOGITS
     a
    0.30
     This
    0.26
     They
    0.26
     It
    0.25
     You
    0.24
     brochures
    0.24
     새로운
    0.24
     We
    0.23
    <unused243>
    0.22
    a
    0.22
    Act Density 0.704%

    No Known Activations