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

    Neuronpedia

    INDEX
    Explanations

    PHP code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pizz
    0.38
     be
    0.37
    綰
    0.35
    हीर
    0.34
     Ketch
    0.34
    plic
    0.34
     Joaqu
    0.33
    лта
    0.33
     Muller
    0.33
    мере
    0.32
    POSITIVE LOGITS
     नसी
    0.39
    ↵
    0.36
    ↵↵↵
    0.34
    或者
    0.33
     विकार
    0.33
    getDoctrine
    0.33
    ‵
    0.33
    あるいは
    0.33
     ।
    0.32
    Соц
    0.32
    Act Density 0.001%

    No Known Activations