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

    Neuronpedia

    INDEX
    Explanations

    python code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Якщо
    0.34
     изделий
    0.31
     FORD
    0.29
     причем
    0.29
    璿
    0.29
     NEA
    0.28
     Як
    0.28
     τότε
    0.28
     কাহার
    0.27
     नाइट्रेट
    0.27
    POSITIVE LOGITS
    /*
    0.32
     fable
    0.32
     desenvolvimento
    0.31
    ْر
    0.30
    abilistic
    0.30
    main
    0.30
    aboration
    0.30
     diverses
    0.29
     പ്രവർത്തന
    0.29
     eer
    0.29
    Act Density 0.107%

    No Known Activations