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

    Neuronpedia

    INDEX
    Explanations

    prepositions like by or from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    有点
    1.18
    kowej
    1.12
    KAK
    1.09
    lastname
    1.07
    making
    1.05
    常见的
    1.05
    Hasil
    1.05
    1.04
     ቀለም
    1.01
     истины
    1.00
    POSITIVE LOGITS
    \,\
    1.04
    ่ะ
    1.03
     Viele
    1.02
    \;
    0.99
    জমেন্ট
    0.94
     pronotum
    0.91
     intellectuals
    0.91
     Parque
    0.89
     physiques
    0.88
     অপরদিকে
    0.86
    Act Density 0.149%

    No Known Activations